Advertisement Private equity has played a significant role in shaping Indi… In today’s real estate landscape, fitness is often treated… In this episode of Prop Personalities, we sit down with Hars… Luxury real estate is one of the most talked-about segments … Welcome to Prop Personalities by Prop News Time – a podcast … TCL Solar presented its latest photovoltaic technologies at the Korea Green Energy Expo in Daegu during the past week, highlighting its focus on South Korea’s expanding solar market. The country is projected to reach a cumulative installed solar capacity of 55.7 GW by 2030, with over 5 GW expected annually. The company displayed high-efficiency modules, including TOPCon and Back Contact technologies, alongside lightweight solutions tailored for ageing industrial rooftops. These offerings are positioned to support distributed and floating solar segments, which are driving market growth. The showcase also reflects TCL Solar’s broader strategy to collaborate with local partners and strengthen its presence in the Korean renewable energy ecosystem. Representative image TCL Solar showcased its latest photovoltaic solutions at the Korea Green Energy Expo in Daegu during the past week, as the company expanded its engagement with South Korea’s growing renewable energy sector. The exhibition comes at a time when the country is targeting a cumulative installed solar capacity of 55.7 GW by 2030, with annual additions exceeding 5 GW, driven by increasing adoption of distributed and floating photovoltaic systems.
Advertisement
The company presented its T5 Pro TOPCon Multi-Cut product, which incorporates advanced Tunnel Oxide Passivated Contact (TOPCon) technology combined with overlapping cell architecture. The module is designed to deliver a maximum power output of up to 670W and 755W, positioning it within the high-efficiency segment of solar energy solutions.
In addition, TCL Solar introduced its C2 Back Contact module, which is engineered to deliver higher energy yields, particularly in complex installation environments. These include projects with high balance-of-system costs, limited land availability, low ground reflectivity, or partial shading conditions. The module’s design eliminates front metal lines and busbars, offering both improved performance and enhanced visual integration with architectural requirements in urban settings.
The Back Contact module also provides a higher power output, exceeding comparable TOPCon modules by approximately 20W, while maintaining improved resistance to hot spots and a lower degradation rate of around 0.35%. Such features are intended to improve long-term efficiency and operational reliability in varied deployment conditions.
The company further highlighted its lightweight module range, weighing approximately 5.4 kg per square metre, which reduces structural load by nearly half. These modules are particularly suited for installation on ageing industrial rooftops, a segment gaining traction in South Korea as part of distributed solar deployment strategies.
Alongside product showcases, TCL Solar acknowledged its local partner, Prana Solution Co., Ltd., for achieving strong sales performance, underscoring the company’s collaborative approach in the Korean market. The firm also pointed to its manufacturing capabilities through its parent, TCL Zhonghuan, including the development of an advanced silicon wafer production facility.
The exhibition participation reflects TCL Solar’s strategy to align with South Korea’s renewable energy targets by offering localised solutions and strengthening partnerships. The company indicated that it would continue working with regional stakeholders to support solar capacity expansion while advancing its international footprint through the Korean market.
Source – PTI Advertisement Have something to say? Post your comment 29th Apr, 2025 1st Oct, 2024 26th Apr, 2024
Advertisement Enter the email ID used to register with us This disclaimer (“Disclaimer”) is applicable to the entire Site. Upon entering the Site it is recommended that you immediately read the Terms and Conditions and Privacy Policy listed therein. Your continued usage of this Site will indicate your unconditional acceptance of the said Terms and Conditions and Privacy Policy. You hereby agree that Prop News Time reserves the right to modify at any time, the Terms and Conditions and Privacy Policy governing this Site without prior notification. Your usage of the Site implies that you will be bound by any such modification. You agree and acknowledge that it is your responsibility to periodically visit the Site and stay updated with the Terms and Conditions and Privacy Policy of the Website. The information contained in this Site has been provided by Prop News Time for information purposes only. This information does not constitute legal, professional or commercial advice. Communication, content and material within the Site may include photographs and conceptual representations of projects under development. All computer-generated images shown on the Site are only indicative of actual designs and are sourced from third party sites. The information on this Site may contain certain technical inaccuracies and typographical errors. Any errors or omissions brought to the attention of Prop News Time will be corrected as soon as possible. The content of this Site is being constantly modified to meet the terms, stipulations and recommendations of the Real Estate Regulation Act, 2016 (“RERA”) and rules made thereunder and may vary from the content available as of date. All content may be updated from time to time and may at times be out of date. Prop News Time accepts no responsibility for keeping the information on this website up to date or any liability whatsoever for any failure to do so. While every care has been taken to ensure that the content is useful, reliable and accurate, all content and information on the Site is provided on an “as is” and “as available” basis. Prop News Time does not accept any responsibility or liability with regard to the content, accuracy, legality and reliability of the information provided herein, or, for any loss or damage caused arising directly or indirectly in connection with reliance on the use of such information. No information given under this Site creates a warranty or expands the scope of any warranty that cannot be disclaimed under applicable law. This Site provides links to other websites owned by third parties. Any reference or mention of third-party websites, projects or services is for purely informational purposes only. This information does not constitute either an endorsement or a recommendation. Prop News Time accepts no responsibility for the content, reliability and information provided on these third-party websites. Prop News Time will not be held liable for any personal information or data collected by these third parties or for any virus or destructive properties that may be present on these third-party sites. Your use of the Site is solely at your own risk. You agree and acknowledge that you are solely responsible for any action you take based upon this content and that Prop News Time is not liable for the same. All details in the form of news stories, photos and videos provided on this Site are updated on the basis of information available from the respective developers/owners/promoters. All such information will not be construed as an advertisement. This Site is for guidance only. Your use of this Site – including any suggestions set out in the Site and or any use of the resources available on this Site, do not create any professional–client relationship between you and Prop News Time. Prop News Time cannot accept you as a client until certain formalities and requirements are met. Cookie Disclaimer We use cookies to give you the best possible service while using our website, please accept it and continue browsing if you’re happy with this. For more information see our Privacy Policy
PropNewsTime is a dedicated property news website that covers the latest events, stories, updates and occurrences in the industry. We are an unbiased entity not affiliated with any builder, broking firm and banking institution.
The U.S. Department of Commerce has issued preliminary anti-dumping determinations for three key solar-exporting nations, establishing duties of up to 123% on crystalline silicon photovoltaic cells and modules. Image: bernswaelz/Pixabay The U.S. Department of Commerce has announced preliminary affirmative determinations in its anti-dumping (AD) duty investigations into solar imports from India, Indonesia, and Laos. According to a fact sheet released by Commerce, the agency determined preliminary dumping margins of 123.04% for India, 35.17% for Indonesia, and 22.46% for Laos. These investigations were initiated last August following a petition by the Alliance for American Solar Manufacturing and Trade, a coalition of domestic manufacturers including First Solar, Hanwha Qcells, and Mission Solar. The group argued that a surge of low-priced imports from these nations was undercutting the U.S. manufacturing sector at a critical period of domestic expansion. These new AD duties are in addition to the preliminary countervailing duties (CVD) announced by the Commerce Department in February 2026, which targeted government subsidies. When combined, the total preliminary duty exposure for many exporters from these countries has risen sharply. For India, total duties now reach approximately 234% for most manufacturers. In Indonesia, combined rates range between 121% and 178%, while in Laos, the total preliminary rate stands at roughly 103%. U.S. Customs and Border Protection (CBP) will now require importers to post cash deposits based on these preliminary rates. The targeted nations represent a massive portion of the U.S. supply chain; according to government data, India, Indonesia, and Laos accounted for $4.5 billion in solar imports in 2025—roughly two-thirds of the total volume entering the country. While these rates take effect immediately as cash deposit requirements, they remain preliminary until final determinations are issued later this year. Final decisions for India and Indonesia are scheduled for July 13, 2026, while Laos is expected to receive a final determination on or around September 9, 2026. The final step in the process rests with the U.S. International Trade Commission (ITC), which must determine if these imports have caused material injury to the domestic industry. The ITC’s final injury determination is currently scheduled for October 19, 2026. If the ITC issues a negative determination, the investigations will be terminated, and all collected deposits will be refunded. If affirmative, final duty orders will be issued on October 26, 2026. The U.S. government ha also announced preliminary affirmative determinations in these countervailing duty (CVD) investigations in late February.
This content is protected by copyright and may not be reused. If you want to cooperate with us and would like to reuse some of our content, please contact: editors@pv-magazine.com. More articles from Ryan Kennedy Please be mindful of our community standards. Your email address will not be published.Required fields are marked *
This website uses cookies to anonymously count visitor numbers. View our privacy policy. The cookie settings on this website are set to “allow cookies” to give you the best browsing experience possible. If you continue to use this website without changing your cookie settings or you click “Accept” below then you are consenting to this. Close
Home → Environment → Renewable Energy Across the U.S., critics are pressuring public officials to stop or stall new solar projects, often citing unfounded health concerns. This story was originally published by ProPublica. Kevin Heath had hoped there would be solar panels by now on his family farm in southeastern Michigan, roughly 50 miles outside Detroit. About six years ago, he agreed to lease part of his land for a solar project. It would help him pay off debt and keep the farm in the family, he said. But the opportunity was thwarted when, in 2023, following pushback from some local residents, his township passed an ordinance that banned large solar projects from land zoned for agriculture. In the fight over solar development, Heath said he was bombarded by just about every argument from critics — including claims that solar fields are a health hazard. “I’ve heard them say that, but I’ve never heard anybody prove that,” Heath said. “The health and safety issue,” he added, “that is just a joke.” Michigan has big prospects in solar farming — measured by the expected growth in the capacity of its farms to add electricity directly to the grid. According to the U.S. Energy Information Administration, most of the nation’s new capacity from this type of solar farm is planned this year for four states, including Michigan. The others, with their hot deserts and big-sky plains, seem more obvious: Texas, Arizona and California. To some, in Michigan and beyond, this growth feels dangerous. They pressure public officials to stop, stall or otherwise complicate new solar projects with an array of arguments that now go beyond just land use to include public health. There is little reputable evidence to back their claims. But health concerns have helped power a solar backlash that undercuts efforts to broaden energy sources even as customer costs are rising. Stay ahead with ZME Science and subscribe. Please check your inbox and confirm your subscription. Restrictions on solar development are proliferating nationwide, “often rooted in misinformation or unfounded fears,” including ones that involve “potential environmental and human safety risks,” according to an article published late last year in the Brigham Young University Law Review. To generate electricity, solar projects harvest energy from the sun. “And that’s really not that different from what a field of corn or alfalfa does,” said Troy Rule, the Arizona State University law professor who authored the article. “In fact, arguably, it’s even more environmentally friendly.” Still, a state board in Ohio rejected an application for a solar project last month, citing local opposition, even though its staff initially said it met all requirements. Along with other concerns, according to the board, opponents “testified about the potential impacts on the health of residents.” A bill in Missouri would halt commercial solar projects in the state, including those under construction, through at least 2027, as a state agency develops new regulations. The bill’s emergency clause says this is “deemed necessary for the immediate preservation of the public health, welfare, peace, and safety.” And, on the eastern edge of Michigan, St. Clair County adopted a novel public health regulation last year that set limits on solar development and battery storage. The move was encouraged by the county’s medical director who, in a memo, warned of the threat of noise, visual pollution and potential sources of contamination. Some local residents have long pressed leaders to act, saying that intrusive noise could worsen post-traumatic stress disorder and other ailments. Public officials don’t always examine the validity of health claims, according to Rule. And local deliberations rarely compare the impact of solar farms to common agricultural practices, which can lead to runoff from fertilizers and herbicides, for example, or waste lagoons from concentrated animal feeding operations. People have many reasons for taking issue with large-scale solar development, said Michael Gerrard, an environmental lawyer and founder of Columbia University’s Sabin Center for Climate Change Law. But as for the feared health impact, he said, “there’s no basis for that.” “People try to come up with a rationale to justify their dislike of things they dislike for other reasons,” Gerrard added. President Donald Trump’s administration, meanwhile, is adding to the skepticism that renewable energy is worthwhile. Among other moves, it’s phasing out federal tax credits for the solar and wind industries. It all takes a toll on the effort to build out solar infrastructure. Last year, new solar installations in the U.S. dropped by 14%. Large solar developments can transform hundreds, or even thousands, of acres of rural land, paneling them with crystalline silicon and tempered glass. It’s a big change, and people have questions. Locals worry that electromagnetism and even glare can pose a health risk. They wonder if toxic materials could leach into the soil and contaminate groundwater, if not while the solar site is operational, then some decades in the future, when it reaches the end of its life. That certainly has been the case with orphaned oil wells, which also were built with promises of safety. But researchers point out that the most common types of panels have only small amounts of such materials, if any. They are encased and unlikely to leach into the soil. Rather than sitting in landfills when a site is decommissioned, most of the materials used in solar panels can be recycled (though the process can be costly). Craig Adair, vice president of development at Open Road Renewables, which has pursued renewable energy projects in several states, has fielded a range of concerns over the years — from how soil could be contaminated to the possibility of electromagnetic fields causing cancer. “Those questions, in just about every case, have an answer,” Adair said. “There is rigorous academic study, and there are examples of projects that have been operating.” While the future farmability of the land is often a concern, many researchers — and farmers — say that a solar lease will help preserve it. With proper planning on the front end, equipment can be removed from a decommissioned solar site and green space restored, said Steve Kalland, executive director of the NC Clean Energy Technology Center, which, along with its partners, provides technical assistance to local governments in the Carolinas. And a person’s exposure to the electromagnetic field, or EMF, from a solar farm is roughly the same as what they would encounter from ordinary household appliances, according to researchers. EMF levels also decrease rapidly with distance. Chronic exposure to noise is also a recurring complaint from critics. In challenging a proposed project from Adair’s company in Morrow County, Ohio, one woman said in a brief to the state siting board that she was troubled about how noise from the facility might affect people with neurological noise sensitivities, including her daughter. A piece of equipment called an inverter is usually the source of noise on a solar site. It converts the current into the form that’s used on the grid. But noise, as well as glare, are typically buffered with vegetative landscaping and setbacks, or the distance between the property line and the nearest structure. Inverters can also be placed far from the ears of neighbors. Noise modeling for the Morrow County project showed that its inverter “will basically be inaudible to the public,” Adair said, and if it ever generated noise above a certain limit, the permit would require the company to bring it back into compliance. The problem, Adair said, is that evidence-based answers and solutions can get lost in the fervor. They can be drowned out by “opposition activists wanting to try to scare local politicians into opposing a project, even if the concerns that they’re raising are not legitimate concerns,” he said. Last month, the Ohio Power Siting Board denied a permit to Adair’s Morrow County project. Its order acknowledged that the proposal offered positive benefits, but, it said, “these benefits are outweighed by the consistent and substantial opposition.” It didn’t specifically cite health concerns as the reason for the denial, but rather, “the varied and numerous concerns raised by both the local government entities and public in the project area.” But, Adair said in an email, those local governments “cited (unfounded) public health concerns as a reason for their opposition to the project.” Open Road Renewables plans to apply for a rehearing from the board, Adair said. The company has eight permitted solar projects in Ohio, but because of a siting process that he said is subject to “manipulation and misinformation,” Adair said it won’t initiate any more. In Michigan’s St. Clair County, it isn’t just a number of residents who are worried about large solar facilities. The Health Department’s medical director echoed their concerns. In twomemos to other county officials, Dr. Remington Nevin said that large solar sites are a public health risk for the area’s predominantly rural residents. The state’s solar standards, he wrote, weren’t enough to protect them from “environmental health hazards, the spread of sources of contamination, nuisance potentially injurious to the public health, health problems, and other conditions or practices which could reasonably be expected to cause disease.” Any detectable tonal noise, he added, must be considered an unreasonable threat to public health. He recommended new regulations. The county administrator at the time, Karry Hepting, noted that Nevin’s initial memo “does not address the question or provide support for what are the potential health/environmental risks,” according to internal emails provided to ProPublica. “It appears we will need to hire an outside expert to get the level of detail and supporting data necessary to consider potential next steps,” she added. Hepting said that she’d begun researching prospects. But County Commissioner Steven Simasko — now the county board’s chair — wrote in an internal email that he accepted Nevin’s medical opinion “as a good standard for the protection of the public health of our citizens” and disagreed with the need for outside input. Simasko told ProPublica in an email that he believed it wasn’t the role of the administrator to get involved in a public health matter, and that he objected “to essentially paying for a second public health medical opinion” more to Hepting’s liking. Hepting, who has since retired from her post at the county, disputed Simasko’s depiction of her motivations in a message to ProPublica. “Nothing could be farther from the truth,” she wrote. “It had nothing to do with shopping for a different opinion. Mr. Nevin’s initial memo did not address the initial question posed by the Board. It did not state what the health risks were and what negative health impacts exist. It basically said it’s a risk because he said so.” To legally justify the adoption of health regulations, Nevin said in his second memo, it wasn’t necessary for his department “to prove, with a precise scientific or medical rationale, that eligible facilities pose an unreasonable threat to the public’s health.” Instead, expert opinion, public comment and the consent of the local government were reason enough, he wrote. In the end, county officials were persuaded to act. The commissioners approved the Health Department’s new policy for solar energy and battery facilities, including a nonrefundable $25,000 fee to cover the cost of reviewing a proposed project. It also said that policy violations were punishable by up to six months in prison. An electric utility promptly sued, and a solar company joined the case. The Health Department, they argued, has no authority to issue what are, in effect, zoning regulations. What’s more, they said in legal filings, the county can’t override the solar standards established by the state. In its legal filings, the county said the health regulations were adopted properly and supported by “substantial, competent, and material evidence.” Facilities that don’t meet its standards “pose a threat to public health,” the county argued. In response to ProPublica’s detailed queries, a public information officer said that the Health Department would not comment due to litigation. Nevin said in a podcast interview last year that he wasn’t opposed to solar projects. “The purpose,” he said, “is to identify risks, unreasonable risks, to the public’s health posed by the construction or operation of the facilities, and then take reasonable, measured steps to attempt to mitigate those risks, ideally in a fashion that would continue to allow the facility to be constructed and to operate.” Solar capacity in Michigan continues to grow, despite local pushback, but so far, only 2.55% of the state’s electricity comes from solar. In Ohio, it’s nearly 6%, according to the Solar Energy Industries Association, a trade group. In Texas, it’s nearly 11%. Michigan is requiring electricity providers to reach an 80% clean energy portfolio by 2035, and 100% by 2040. Michigan has more local restrictions on renewable energy than any other state, according to the Sabin Center. “Practically nowhere in the country has seen more conflict” about where to allow large solar farms that add electricity directly to the grid than rural Michigan, according to a 2024 article in the Case Western Reserve Law Review authored by a Sabin Center senior fellow. That includes the conflict in Milan Township, where Heath grew up on an 1,100-acre farm. “I always wanted to farm,” Heath said. He saw leasing part of his land to a solar company as a way to stay afloat and keep the land in the family. In 2020, Milan Township passed an ordinance that would allow the project to go forward, with Heath’s brother, the township supervisor, abstaining. But opposition mounted. Critics built a website that argued, among other things, that the project would unleash dangerous electromagnetic radiation. Heath and his siblings were rebuked by their neighbors, Heath said, to the point that his brother, Phil, told the township attorney he was thinking about resigning as supervisor. That same night, he died of a heart attack at age 67. A few months later, with a new supervisor in place, the township board banned large solar development from land that’s zoned for agriculture. The terms were restrictive enough to effectively ban such a project not only from land owned by Heath and his sister, but from all but the small portion of the township that’s zoned for industry. Stephanie Kozar, Milan Township’s clerk, said in an email to ProPublica that most residents opposed solar projects on agricultural land, and that the initial ordinance passed during the coronavirus pandemic, before officials had adequately informed residents about potential changes. The updated policy, she said, would “protect the township and allow for responsible development of clean energy in the area.” To overcome severe local restrictions, the state set standards in 2023 for noise, height, fencing, setbacks and other elements of a large solar project. It also created a pathway where developers, in certain cases, can get a permit from the Michigan Public Service Commission, the state’s regulating authority, rather than from local governments. In an order, the commission laid out details for how the process would work. But nearly 80 local and county governments, including Milan Township, challenged it in court, arguing the commission was overstepping its authority. In support of the state, Heath and his sister are represented in a friend-of-the-court brief filed by a legal team affiliated with the Sabin Center, along with local attorneys. Also part of that brief is Clara Ostrander, who had hoped a solar project would help protect two farmsteads in Milan Township that have been in her family for over 150 years. “We need a responsible neutral party like the Michigan Public Service Commission to review these projects based on facts, not fear or falsehoods,” she testified to state officials ahead of the bill’s passage. Even with the state process, rising energy demand and eye-popping electricity costs, no new large solar installation has yet been built in Milan Township. And in February, as snow melted around the “No Industrial Solar” signs that stud the long country roads, a circuit court judge ruled that St. Clair County’s health regulation is “invalid, null, and void.” But county officials soon opted to appeal, unanimously. “This is very important for the health of St. Clair County and the residents,” said one commissioner before casting his vote.
A two-year field study in a 100 MW photovoltaic plant in semi-arid Inner Mongolia combined ground-based sensors, radiation measurements, and UAV thermal imaging to quantify how large-scale PV installations alter local air temperature, surface temperature, and energy balance compared with nearby non-PV areas. Results show consistent site-scale warming of 0.8 C. Inner Mongolia, China Image: Svdmole, Wikimedia Commons, CC BY-SA 3.0 A research team from China conducted a two-year field study to assess how large-scale photovoltaic (PV) farms influence local climate conditions, with a focus on air temperature, surface temperature, and surface radiation balance. The observation campaign took place from 2022 to 2024 at a 100 MW solar PV facility located in a semi-arid desert region of Inner Mongolia. The researchers combined in situ meteorological measurements, surface radiation observations, and uncrewed aerial vehicle (UAV)-based thermal infrared imaging to quantify changes in air temperature, land surface temperature, and the surface energy balance. By comparing conditions within the PV installation and in nearby non-PV reference areas, they assessed how PV infrastructure alters radiative fluxes and heat exchange processes in dryland environments. The dataset provided high-resolution evidence of how utility-scale PV deployment can modify local thermal regimes and energy partitioning in arid and semi-arid landscapes, offering insight into the broader environmental impacts of rapid solar energy expansion. “Our study aims to quantify the seasonal and diurnal impacts of PV deployment on near-surface air temperature; to characterize the fine-scale spatial heterogeneity of land surface temperature (LST) within and around PV arrays using UAV-based thermal imaging; and to diagnose the radiative and thermodynamic mechanisms underlying PV-induced warming by combining ground-based and aerial observations,” explained the researchers. During the study period, a network of temperature sensors was deployed both within the PV plant and at a nearby reference site located approximately 10 km away to capture background conditions unaffected by solar infrastructure. These instruments were installed at a standard height of 2 m above ground level and recorded air temperature at 15-minute intervals, enabling high-temporal-resolution comparisons between the PV and non-PV environments. In addition to the long-term temperature monitoring, targeted radiation measurements were conducted during an intensive field campaign in July 2023. This campaign used instrumented observation towers positioned inside the PV field and at a reference location about 2 km away, allowing the researchers to directly compare radiative fluxes under similar meteorological conditions. To complement the point-based measurements, land surface temperature patterns were further examined using UAV-based thermal infrared imaging on July 29, 2023. This approach provided high-resolution spatial mapping of surface thermal conditions across both the PV installation and adjacent non-PV areas, capturing fine-scale heterogeneity that ground sensors alone could not resolve, according to the research group. The results showed a statistically robust warming signal associated with the PV installation. Over the two-year observation period, the PV farm exhibited a mean air temperature increase of 0.8 C relative to the reference site, with warming observed consistently across all seasons. The study further found an asymmetry in diurnal temperature changes: increases in daily minimum air temperatures were greater than those in daily maximum temperatures, leading to a 1.9 C reduction in the daily temperature range compared with non-PV areas. Consistent with these findings, UAV-based thermal mapping revealed elevated land surface temperatures within the PV field, ranging from 0.3 C to 4.1 C above adjacent non-PV regions. The radiation measurements also indicated a positive perturbation in surface energy balance, with mean daily net radiation increasing by 8.3 W m² in the PV area. This enhancement was particularly pronounced during daytime hours, when net radiation rose by up to 18.5 W m², highlighting the role of PV infrastructure in modifying local radiative and thermal dynamics. “This increase in net radiation was primarily due to a decrease in albedo, which resulted in 24.6 W m2 more net shortwave radiation,” the team said. “The PV farm increased the outgoing longwave radiation by 6.1 W m2 during the daytime and 4.6 W m2 at night, which was considerably lower than the increased net shortwave radiation.” The research was presented in “Persistent site-scale warming associated with solar photovoltaic installations,” published in the Journal of Environmental Management.“These findings underscore the need to consider potential environmental trade-offs in future PV deployment strategies,” the scientists concluded. Researchers from China’s Inner Mongolia University of Finance and Economics, Peking University, Inner Mongolia Institute of Water Resources Research, and Inner Mongolia Agricultural University. This content is protected by copyright and may not be reused. If you want to cooperate with us and would like to reuse some of our content, please contact: editors@pv-magazine.com. More articles from Lior Kahana Please be mindful of our community standards. Your email address will not be published.Required fields are marked *
This website uses cookies to anonymously count visitor numbers. View our privacy policy. The cookie settings on this website are set to “allow cookies” to give you the best browsing experience possible. If you continue to use this website without changing your cookie settings or you click “Accept” below then you are consenting to this. Close
Following the signing of the contract for the construction of the Jacmel photovoltaic solar power plant at the Mont Fleury site (https://www.haitilibre.com/en/news-46650-haiti-technology-construction-of-a-major-solar-power-plant-in-jacmel.html), Joseph Almathe Pierre Louis, the Minister of Public Works (MTPTC), instructed the teams to expedite the development work on certain road sections with the technical support of the Southeast Departmental Directorate (DDSE-Jacmel). This breakthrough not only benefits the energy project but also represents a major improvement in access for the local population of Mont Fleury (6th communal section of Jacmel). It is worth noting that the Ministry of Public Works (MTPTC) is acting as the project owner and is ensuring the rigorous supervision and monitoring of the progress of the photovoltaic solar power plant, which is being built with over $17 million in funding from the World Bank through the Renewable Energy for All in Haiti (SREP) program. The contractor, the Dominican international firm ESD Engineering Service S.R.L., is responsible for delivering a state-of-the-art, turnkey solution. The installations will include: • A 4 MW solar power generation capacity (minimum output of 3.35 MW); • A 6 MWh battery energy storage system (BESS) using lithium-ion technology; • Grid expansion with the installation of approximately 4 km of low-voltage lines and 7 km of medium-voltage (23 kV) lines. Thanks to its grid-forming technology, this power plant will guarantee the stability of the electrical grid, even in the event of a shutdown of the current thermal power plant or during periods of low sunlight. Construction of this power plant is expected to take 13 months, from February 2026 to March 2027. See also : https://www.haitilibre.com/en/news-46650-haiti-technology-construction-of-a-major-solar-power-plant-in-jacmel.html HL/ HaitiLibre
Enter your password Published on 04/27/2026 at 04:57 pm EDT EGing Photovoltaic Technology Co.,Ltd. reported earnings results for the first quarter ended March 31, 2026. For the first quarter, the company reported sales was CNY 169.99 million compared to CNY 608.16 million a year ago. Net loss was CNY 65.48 million compared to CNY 53.14 million a year ago. Basic loss per share from continuing operations was CNY 0.06 compared to CNY 0.04 a year ago. Diluted loss per share from continuing operations was CNY 0.06 compared to CNY 0.04 a year ago. Currency / Forex Commodities Cryptocurrencies Interest Rates Best financial portal More than 20 years at your side + 1,300,000 members Quick & easy cancellation Our Experts are here for you OUR EXPERTS ARE HERE FOR YOU Monday – Friday 9am-12pm / 2pm-6pm GMT + 1 Select your edition All financial news and data tailored to specific country editions NORTH AMERICA MIDDLE EAST EUROPE APAC
The new photovoltaic system on the roof of Borussia Dortmund’s SIGNAL IDUNA PARK has been completed. With an output of more than 5 megawatts (MWp), the club is now proud to have the world’s most powerful PV system ever installed on a stadium roof. With 11,132 modules and an output of more than 5 megawatts (MWp), Germany’s largest stadium now boasts the world’s most powerful PV installation on a stadium roof. In the future, BVB will cover up to half of the stadium’s electricity needs using solar energy. The world record has been officially confirmed by the German Record Institute. Compared to the previous power supply, the system saves approximately 1,700 tonnes of CO₂ per year.
The new photovoltaic system of the roof of SIGNAL IDUNA PARK. Image: BVB
By the beginning of 2026, a battery storage facility with a capacity of 3.7 megawatt hours will also have been built. Once it has been connected to the new PV system, climate-friendly electricity can also be used when the sun is not shining. PV System and Battery at SIGNAL IDUNA PARK
– Installed PV capacity: 5.009 MWp (previous system: 0.924 MWp) – Most powerful stadium-roof PV system worldwide – 11,132 JA Solar Fullblack modules (450 Wp/module) – 11 Sungrow inverters – Self-consumption rate approx. 45% – Completion of the battery storage system (stationary battery): Q1/2026 – Installed storage output: 3.7 MW – Approx. 4.1 GWh/year savings Back in April 2024, BVB and RWE installed a PV system with around 200 solar modules on the roof of the BVB FanWelt next to the stadium. As “Premium & Sustainability Partner,” RWE supports BVB in its ambitious decarbonization plans. The Johan Cruijff ArenA in Amsterdam is also relying on a battery storage solution at the stadium. Entire matchdays can already be powered exclusively by green energy. stadiaworld visited the venue to see how the system works and how those in charge are already planning the next steps.
Hans-Joachim Watzke, Chairman of the Management Board BVB: “SIGNAL IDUNA PARK symbolizes our integrated efforts to ensure Borussia Dortmund’s future viability. We are delighted that our iconic home can now be associated with a record-breaking flagship project for climate protection.” (stadiaworld, 24.11.2025)
Continue reading with Your benefits with stadiaworld+ Register now Do you already have a Stadionwelt+ or stadiaworld+ subscription? Log in here
Let Utility Dive’s free newsletter keep you informed, straight from your inbox.
In partnership with In partnership with The American Energy Dominance Act would remove the accelerated deadlines that the One Big Beautiful Bill Act placed on the renewable energy 45Y production tax credit and 48E investment tax credit. Republican lawmakers in the House of Representatives are trying to restore clean tax credits for wind, solar and other clean energy technologies that were curtailed by theOne Big Beautiful Bill Act. The American Energy Dominance Act, introduced Thursday, would remove the accelerated deadlines that the One Big Beautiful Bill Act placed on the renewable energy 45Y production tax credit and 48E investment tax credit, and make similar changes to other impacted credits, like the 45V clean hydrogen production credit. The bill was introduced by Rep. Brian Fitzpatrick, R-Pa., Rep. Max Miller, R-Ohio, Rep. Mike Carey, R-Ohio, and Rep. Mike Lawler, R-N.Y. A release from Fitzpatrick’s office said the legislation was “developed in direct partnership with the North America’s Building Trades Unions.” “Under current law, key incentives such as 179D and 45L are scheduled to expire on June 30, 2026,” said the release. The legislation would “fully restore” the 179D, or Energy Efficient Commercial Buildings Deduction credit, without a scheduled expiration. “For capital-intensive sectors, a shortened policy horizon does more than disrupt planning — it raises the risk that critical projects are delayed, scaled back, or never built at all,” the release said. “When that happens, it is American workers, American employers, and American families who pay the price through slower growth, tighter energy supply, and continued cost pressure.” E2 estimated that $34.8 billion in clean energy investments were canceled in 2025, outnumbering new investments three to one. In a Friday release, E2 executive director Bob Keefe called the legislation a “modest – but smart – step back in the right direction.” Capstone analyst Andrew Lascaleia said in a Saturday research note that the firm does “not expect [Fitzpatrick’s] bill that would reverse many of the changes made to energy tax credits under the One Big Beautiful Bill Act to gain traction in this Congress.” “However,” Lascaleia added, “we believe the bill, which would restore clean electricity, hydrogen, and energy efficiency tax credits, may find support if Democrats win the House or Senate in the 2026 elections. This would benefit renewables developers and manufacturers.” Democratic lawmakers in March introduced a clean electricity bill that would, among other measures, restore clean energy tax credits that were eliminated by the OBBBA. Fitzpatrick’s office did not respond to a request for comment. Get the free daily newsletter read by industry experts Gas power M&A valuations have doubled since 2024, but new generation remains a risky investment, analysts say. DOE’s colocation proposal and transmission planning reforms will set FERC’s agenda this year against a backdrop of rising concern over affordability, former commission chairmen and experts say in our 2026 outlook. Subscribe to Utility Dive for top news, trends & analysis Sign up for the free newsletter. Interested? Explore more of what has to offer. Thanks for signing up! Please keep an eye out for a confirmation email from [email protected] To ensure we make it into your inbox regularly, add us to your allow list, mark us as a safe sender, or add us to your address book. Check out more from Get the free daily newsletter read by industry experts Gas power M&A valuations have doubled since 2024, but new generation remains a risky investment, analysts say. DOE’s colocation proposal and transmission planning reforms will set FERC’s agenda this year against a backdrop of rising concern over affordability, former commission chairmen and experts say in our 2026 outlook. The free newsletter covering the top industry headlines
We have a number of email newsletter options that you can choose to subscribe to, including a topic with news and updates for waste and recycling. You can sign up for updates or access your subscriber preferences on our email updates system. On Wednesday, April 8, the Secretary of State for Energy Security and Net Zero approved plans for Springwell Solar Farm, which would be the UK’s largest solar farm. The site would cover around 1,280 hectares of land near Scopwick in North Kesteven.
During the planning process, Lincolnshire County Council and North Kesteven District Council argued strongly against the development, citing that the application did not properly assess the impacts on our rural villages and landscapes, or adequately take into account the cumulative impact of developments in Lincolnshire, which continue to use large amounts of the best and most versatile agricultural land – of which there is limited in the country. Having carefully reviewed the Examining Authority’s report and Secretary of State’s decision letter, the councils are concerned that the proper process was not followed and are now seeking to challenge the decision legally.
Cllr Sean Matthews, Leader of Lincolnshire County Council, said: “Following legal advice and a careful consideration of the potential costs and impact, we believe we may have grounds to challenge this decision.
“With Lincolnshire bearing the brunt of NSIP applications, it’s important we take a stand, and use the appropriate means to try and stop these developments where possible. If the courts agree that we have grounds to challenge, we’d be in a position to launch a judicial review into this decision.”
Cllr Richard Wright, Leader of North Kesteven District Council, also raised concerns, saying that: “In any planning decision, weighing and balancing competing issues is fundamental to coming to a decision. In this case, it appears that because of process and procedural flaws, the wrong weight has been applied leading to a decision that is arguably unsound”. For the latest news on North Kesteven District Council visit our council news pages Follow us on X (formerly known as Twitter), find us on Facebook, or sign up to our newsletter Find and talk with us online, or contact us directly by online form or email
IMPARTIAL NEWS + INTELLIGENT DEBATE Account Germany has emerged as a global leader in 'plug-in' solar power On arrival in Berlin it doesn’t take long to spot a solar panel. They adorn the roofs and balconies of many of the homes that sit along the main train route from the airport into the city. Germany has emerged as a global leader in “plug-in solar”, with more than one million systems now registered. These are a type of lightweight panel that can be plugged into the mains without an electrician, providing a cheaper and easier entry option for households interested in benefitting from free energy from the sun. POLITICS
Zack Polanski, leader of the Green Party of England and Wales, has said he would much rather see left-leaning figures like Angela Rayner or Andy Burnham leading the rival party than Sir Keir Starmer. Polanski told Sky News: “It is no secret that Burnham and Rayner would be much closer to my politics”. He suggested that under different leadership, he could reassess a potential election pact. However, he caveated that he did have “reservations about their policies”. The Green Party leader admitted he would prefer a Government led by one of the more progessive Labour politicians.
“I do think it’d be a significant improvement to remove Starmer and make sure that the party as leaning more towards the left,” he said.
He added he wants to see an end to “rip-off Britain”. Over the past decade, the amount of time we are expected to remain healthy for has fallen by two years, with experts warning the country is “going backwards”. 73% The proportion of life a woman spends in good health declined from 77 per cent to 73 per cent between 2012 and 2014.
For men, it declined from 79 per cent to 77 per cent.
51 years In Blackpool, the healthy life expectancy (HLE) was just 51 years old for men.
Women in Hartlepool had the same shockingly low HLE. Unlike other comparable countries seeing steady improvement, the Health Foundation’s research found the British population’s health is poor and worsening.
In more than 90 per cent of the UK, the HLE was now lower than the state pension age, the study found. LIFESTYLE 7 min read These findings reveal a stark truth – the UK’s health is going backwards. The lights on the dashboard are flashing red. More people than ever before are living with chronic health conditions. FILM
Audiences were undeterred by widespread critical panning, turning out in their droves for the opening weekend of the controversial Michael Jackson biopic.
This comes seven years after Leaving Neverland, the documentary about Jackson’s alleged sexual abuse of children. FILM 5 min read The singer’s nephew, Jaafar Jackson, plays the titular role alongside Colman Domingo as his father, Joe.
Despite recent high-profile allegations of child sexual abuse, Jackson’s popularity endures. The i Paper‘s film critic, Francesca Steele, argued the flick should never have been made. Steele’s review characterised the film as an obvious attempt to rehabilitate the star’s reputation. She added that the film was not only “misrepresentative” but also “wildly incendiary”. More than 30 children’s toys have been recalled from major UK retailers including M&S and Primark since the beginning of the year. Dozens of children’s sand-based toys have now been recalled over fears they may be contaminated with asbestos. In January, Hobbycraft withdrew its Giant Box of Craft kits after a customer alerted it to asbestos traces in the bottles of sand. The Office for Product Safety and Standards (OPSS) issued new guidance on the most reliable tests, which has led to an increase in contamination concerns. The OPSS needs to take action and ensure proper checks are being carried out to keep dangerous products off the shelves. It should also examine whether toys containing asbestos are being sold on online marketplaces strikes
The council and union are close to striking a deal after a breakthrough in the bitter year-long dispute over jobs and pay. Members of the Unite union walked out in a dispute over pay in March 2025. They argued council plans to remove a role in its waste recycling and collection service would lead to pay cuts. Rubbish piled high on the streets of Birmingham, causing frustrated residents to complain of rodents, strong smells and other health hazards. Council leader John Cotton said he is hopeful the deal will be agreed.
A view of the solar farm site at Duckinfield House Farm, on Hurst Lane(Image: Local Democracy Reporting Service) Controversial plans for a new solar farm in Glazebury have been approved. Duckinfield Solar Ltd's application proposing the development of an up to 10mw solar farm and associated infrastructure on land at Duckinfield House Farm, on Hurst Lane, came before Warrington Borough Council's development management committee on Thursday. The site is located in the green belt. According to a report to the committee, the application site consists of two parcels of agricultural land which are approximately 16ha in size, with the fields bisected by a public right of way (PROW) which cuts across the site and runs along its northern boundary. The report said: "This application proposes a 10 megawatt solar farm with associated infrastructure. The solar panels would be located in both of the fields forming the site either side of the PROW and would have a maximum height of 3.2m. "An access track would be created from the farm into the larger field via the existing level crossing to provide access to the solar installation. To the north-eastern corner of this field there would be a customer substation, a district network operator substation, a storage container and office/welfare facility, as well as a weather station. "Four transformer stations would be positioned along the proposed access track running along the eastern boundary of the site. The solar installation would be enclosed with 2.1m high deer fencing with CCTV towers at a maximum of 3m in height. A temporary construction compound is also proposed to the north-west of the existing farm buildings to the northern side of the railway line." The application was publicised by 29 neighbour notification letters, by site notice and by press notice. According to the report, one letter of support was received with no reasons given in the response. And objections were received from 43 addresses, as a result of the publicity given to the application. The concerns raised, as summarised in the report, included inappropriate development in the green belt, loss of best and most versatile agricultural land, harm to outlook from nearby dwellings and the impact of glint and glare. Ward councillor Matt Smith, ward councillor Cllr Neil Johnson and Culcheth and Glazebury Parish Council also objected to the application. But in the planning officer's report, it said subject to conditions there would be 'no unacceptable impacts' on the local highway network, residential amenity and flood risk. One of the conditions is that the planning permission will be limited to a period of 40 years. Cllr Smith, speaking against the plans, expressed 'strong concerns' over the application. He said: "While I understand the importance of renewable energy, this specific location for a sizeable solar farm will have a significant adverse impact along the valued and well-used public right of way that bisects the site." Cllr Smith also stated the period of 40 years is 'not temporary in the context of a human lifetime, or the enjoyment of our local landscape'. "We should not sacrifice Glazebury's rural character and the quality of our public rights of way for a project that even the case officer admits causes significant landscape harm," he added. "There are undoubtedly more appropriate locations that would have less impact, or less than a substantial adverse impact, on the openness and amenity of our green spaces." Cllr Steve Parish, deputy chair of the development management committee, said: "I think it's fairly obviously Government policy that we need solar energy, and that's before the Middle East was set on fire." He also stated 'we do have a climate emergency'. Furthermore, Cllr Parish described the application as a 'delicate one because of the planning balance'. "But given the emphasis on the need and the idea that 40 years is temporary, and from what I know of other mitigations and other cases, I think we'd have little chance at appeal, frankly," he added. As recommended, the application was approved subject to conditions. To find all the planning applications, traffic diversions, road layout changes, alcohol licence applications and more in your community, visit the Public Notices Portal.
At Reach and across our entities we and our partners use information collected through cookies and other identifiers from your device to improve experience on our site, analyse how it is used and to show personalised advertising. You can opt out of the sale or sharing of your data, at any time clicking the "Do Not Sell or Share my Data" button at the bottom of the webpage. Please note that your preferences are browser specific. Use of our website and any of our services represents your acceptance of the use of cookies and consent to the practices described in our Privacy Notice and Terms and Conditions.
A fire involving rooftop solar panels was reported Monday at a single-family home on Conrad Court in Damascus.
Crews from Montgomery County Fire and Rescue Service responded to smoke coming from the roof and quickly extinguished the fire with no extension into the home. Firefighters successfully deployed a recently acquired tool called “PVStop,” a handheld device that applies a liquid tarp to deactivate solar (photovoltaic) panels, improving safety during suppression efforts. According to Chief Spokesperson for MCFRS Pete Piringer, the fire is believed to have started accidentally, possibly due to a bird’s nest under or near the panels igniting from accumulated heat, though the exact cause remains under investigation. Update – Conrad Ct, Damascus, SFH, solar panel ignited, fire extinguished, no extension, @mcfrs successfully utilized recently acquired ‘PVStop’ a handheld unit to safely apply deactivating liquid (liquid tarp) onto damaged photovoltaic (PV) arrays (solar panels) https://t.co/1EI48eJGsqpic.twitter.com/VWJxu5hPzU — Pete Piringer (@mcfrsPIO) April 27, 2026
Delaware’s largest rooftop solar project is now online with state leaders hoping it marks a turning point for renewable energy across the state. The massive rooftop installation at Delmarva Corrugated Packaging in Kent County is expected to generate about 30% of the company’s daily power needs, reducing costs and easing demand on the regional power grid. Stream Philadelphia News for free, 24/7, wherever you are with NBC10. The project comes as solar energy continues to grow nationwide. Data from the U.S. Energy Information Administration shows solar generation increasing year over year while costs have dropped significantly over the past few decades. Combined with improvements in battery storage, wind and solar now generate more than 17% of the country’s electricity. In Dover, the nonprofit Energize Delaware is helping drive that momentum. The group also operates solar-powered electric vehicle chargers that offer free and clean energy to drivers. Breaking news and the stories that matter to your neighborhood. “It’s actually our largest investment in Kent County and it’s phenomenal work they’re doing,” Drew Slater of Energize Delaware said. “They built the building 30% more efficient than what a standard building would be and now they’ve added solar on top of it. It’s just furthering their own sustainability goals.” The rooftop array itself spans about 10 acres — space that otherwise would have gone unused. Advocates say rooftop solar offers an alternative to building arrays on open land, though challenges remain. Large buildings often need to be constructed or retrofitted to support the weight of solar panels which has limited widespread adoption so far. Still, as technology improves and costs continue to fall, more businesses and property owners may follow suit. “I think it’s a great sign of things to come,” Slater said. While projects like this won’t solve all of Delaware’s energy challenges, supporters say every addition helps — and this one is already making an impact. This story was originally reported for broadcast by NBC Philadelphia. AI tools helped convert the story to a digital article, and an NBC Philadelphia journalist edited the article for publication.
ENGIE South Africa and Pele Green Energy officially inaugurated the Graspan photovoltaic plant in the Northern Cape on 21 April 2026. The 75 MW facility has been supplying the national grid for several months. Each week: 40 curated articles via our newsletters + a selection of your choice. Sector alerts and personalized feed. Just your email — that's all it takes.
Boviet Solar may soon come under Indian ownership. The current parent company of the solar panel brand, Ningbo Boway Alloy Material, announced a plan to sell 100% of Boviet Solar to INOX Solar Americas, the U.S. division of India-based Inox Clean Energy. The Ningbo Boway board of directors unanimously approved the proposal this month. The…
Monday, April 27, 2026 Mohul Ghosh Apr 27, 2026 In a major trade development, the United States has imposed a preliminary anti-dumping duty of 123.04% on solar cells and modules imported from India. The move is expected to significantly impact India’s solar export sector and reshape global trade dynamics in renewable energy. The US Department of Commerce concluded that Indian solar products were being sold below “fair market value” in the American market. This effectively more than doubles the cost of Indian solar exports in the US, making them far less competitive. The decision stems from complaints by US-based solar manufacturers, who argued that: The US government sided with local industry players, aiming to protect domestic solar manufacturing and jobs. This move is being seen as a major setback for Indian exporters, especially since the US is a key market. However, there’s a silver lining: many Indian companies had already started diversifying into other markets, reducing dependence on the US. India isn’t the only country affected: These three countries together accounted for around $4.5 billion of US solar imports, making this a broad move against Asian solar supply chains. Until then, uncertainty remains high for exporters. This is part of a larger global trend: For India, this could accelerate a pivot toward domestic demand and new export markets like the Middle East, Africa, and Europe. The 123% duty isn’t just a tariff—it’s a signal. It shows how strategic sectors like solar are now tied to economic nationalism and global competition, where pricing, policy, and politics intersect. Image Source
Update 4/27: EcoFlow has extended its Earth Day Sale event for an unknown amount of time longer, so be sure to get orders in, as it’s highly likely to end very soon. EcoFlow has launched its Members’ Festival x Earth Day Mega Sale with up to 62% discounts, member-only deals (sign-up is free), 3x EcoCredit rewards, and plenty of free gifts. One notable members-only bundles is the DELTA 3 Ultra Plus Portable Power Station with a FREE Power Hat at $1,449 shipped, which matches in price at Amazon without getting the Power Hat. This unit on its own normally goes for $2,899 at full price, which has consistently been keeping down between $1,499 and $1,449 since 2026 began. While we’ve only seen this rate beaten by one-time falls to $1,424 during Black Friday and the $1,399 low during January’s Winter Storm Sale, making this the next-best price with $1,450 slashed from its tag – plus, you’re getting the $99 Power Hat totally free for $1,549 in total savings. Head below to learn more about it, get the rundown on all the extra savings opportunities, and browse the full sale lineup. Let’s start with a quick breakdown of all the extra savings opportunities during this Earth-focused sale event, like the extra 5% automatic savings you’ll gain in your cart when purchasing one of the many solar generator bundles (power station + solar panels). From there, you’ll also be able to score 3x EcoCredit rewards on many units, and orders of $3,000 or more will receive two FREE 160W solar panels, though I want to point out that this deal will not stack with the extra 5% solar generator bundle savings. The EcoFlow DELTA 3 Ultra Plus is the pinnacle of the brand’s DELTA 3 series of power stations, with an impressive starting 3,072Wh LiFePO4 capacity that expands as high as 11kWh using several different batteries from alternate models in the series, adding to its above-average versatility. It provides 11 port options for connection needs (5x AC, 3x USB-C, 1x USB-A, 1x DC, and a car port), and delivers up to 3,600W of power that can boost to 4,600W when activated, as well as surge up to a max 7,200W. There are six ways to recharge its battery. There’s the usual AC outlet charging that can push it to 80% in up to 89 minutes, as well as gas generator charging, car port charging, which is inferior to using an alternator charger, and up to 1,600W of solar panel charging. There’s also some dual charging options, letting you simultaneously charge via solar and a generator, or solar with an alternator charger. ***Note: The extra 5% savings have been factored into the prices below, and will be automatically applied in your cart. You can also find flash sales throughout this overall sale on the main landing page here, and we also recently spotted EcoFlow launching its new TRAIL Plus 300 DC Portable Compact Power Station (alongside two solar bundle options) starting from $199, too. You’ll find all these and more from other brands collected into our dedicated power stations hub here. FTC: We use income earning auto affiliate links.More. Subscribe to the 9to5Toys YouTube Channel for all of the latest videos, reviews, and more!
by Pranab Mohanty | April 27, 2026 2:04 pm Synopsis: Premier Energies Limited has introduced the NeoBlack Series, India’s first All-Black G12R DCR solar module, at RenewX Chennai. This high-efficiency module, with a capacity of up to 630 Wp, uses advanced TOPCon technology. It combines attractive design with strong performance to encourage urban solar use. In a regulatory filing on April 27, 2026, Premier Energies Limited announced a significant product breakthrough by unveiling the NeoBlack Series. This new lineup features India’s first All-Black G12R DCR solar module, with power outputs ranging from 600 Wp to 630 Wp. The key innovation is its uniform black design, which fits well with modern architecture and reduces glare. The NeoBlack Series is designed to meet the aesthetic needs of urban homeowners and high-end commercial developers, a group increasingly influenced by initiatives like PM Surya Ghar. In addition to its appealing looks, the module offers effective anti-PID (Potential Induced Degradation) performance and improved durability in low-light conditions. To build long-term confidence among investors and consumers, the company offers a 12-year product warranty and a 30-year power output warranty. The market reacted positively to the product launch and the company’s focus on the high-margin residential sector. As of April 27, 2026, Premier Energies shares are trading at Rs. 1,017.70, up Rs. 10.15 or 1.01% from the previous close. The stock hit an intraday high of Rs. 1,027.65, demonstrating strength while the broader Nifty 200 index remains relatively flat. With a total market capitalization of Rs. 46,119.36 crore, the stock has demonstrated strong momentum recently, posting 13.91% returns over the last month and 20.17% year-to-date. Premier Energies Limited is one of India’s largest manufacturers of solar cells and modules, with a history of 30 years. Based in Hyderabad, the company focuses on designing and producing high-efficiency solar cells and modules. Premier Energies is known for its technological leadership, being among the first in India to adopt TOPCon technology. The company also enjoys a strong workplace culture, having received the “Great Place to Work” certification for five consecutive years. It is a key player in India’s efforts toward energy independence. Disclaimer: The views and investment tips expressed by investment experts/broking houses/rating agencies on tradebrains.in are their own, and not that of the website or its management. Investing in equities poses a risk of financial losses. Investors must therefore exercise due caution while investing or trading in stocks. Trade Brains Technologies Private Limited or the author are not liable for any losses caused as a result of the decision based on this article. Please consult your investment advisor before investing.
Pranab is a financial analyst with experience in equities and financial modeling, with a strong understanding of data-driven analysis and quantitative techniques. He has written several analytical pieces and is deeply interested in market trends and valuation. Blending analytical thinking with financial insight, he explores strategies to better understand markets and support informed investment decisions. Trade Brains is India’s trusted financial and business news portal. Phone: 080884 91790 Email: [email protected] Reach us out at For Advertisement, Press Releases, Partnerships or to get backlinks on this website, please e-mail us at [email protected] For Partnerships & Promotio Visit – tradebrainsawards.com/ Chandan Singh Rawat Emaill: [email protected] Mob: (+91)6366648573 Bikram Singhary Email: [email protected] Mob: (+91)8088491790
Solar design platform Solesca has launched Engineering Mode, a new workflow that lets commercial and large-scale solar teams take a project from preliminary design to a stamp-ready interconnection plan set in minutes. Any rooftop, canopy or ground-mount project can now be estimated and engineered in a single session, without leaving the platform. Work that previously…
“With today’s bill, we are paving the way for ‘balcony photovoltaics,’ giving every Greek citizen the opportunity to reduce their energy costs,” said Environment and Energy Minister Stavros Papastavrou on Monday, during the discussion of the draft law concerning the modernization of legislation on the use and production of energy from Renewable Energy Sources (RES). As Papastavrou explained, “the RES Directive we are incorporating sets precise targets, establishes rules, specifies definitions, criteria, and updates the existing framework.” It is “a piece of legislation through which we strengthen energy democracy by simplifying procedures and accelerating the sustainable energy transition, enhancing citizen participation in the energy market with transparency, and further increasing the share of renewable energy sources in the energy mix.” “That is why I speak of energy democracy. The sun and the wind belong to all citizens. And with today’s bill, we are opening the way for ‘balcony photovoltaics.’ The 800W systems we are enabling allows every Greek citizen to reduce their energy costs, thus putting the concept of energy democracy into practice,” he stressed. Referring to the discussion on “small photovoltaics,” the minister noted that “out of the 18 GW of RES entering our energy mix, about 9.2 come from Hellenic Electricity Distribution Network Operator, meaning low and medium voltage. Of these, at least 80,000 photovoltaic installations are small-scale systems. This represents one of the highest penetration rates in Europe, proving that in Greece energy concerns everyone – the many, not the few.” Regarding the European Directive included in the bill, Papastavrou pointed out that it applies to all member states, which have different speeds in terms of RES penetration. “Therefore, it does not have the same impact on all countries. Some, like Greece, have already achieved their targets and are even leading in the share of energy from sun and wind in the energy mix. We rank seventh globally. Other countries need these simplifications much more to boost RES penetration,” he observed, adding: “The goal remains affordable, abundant energy for citizens, with a diversified energy mix, reduced dependence on imported fossil fuels, and energy resilience and security for both citizens and businesses.” Regarding provisions related to NATURA areas, he emphasized that “we are trying to bring order while protecting the biodiversity of each region.” As he noted, “as of today, entire cities fall within the Natura 2000 network: Ioannina, Kastoria, islands such as Chalki and Skopelos, as well as important public infrastructure like airports and ports.” source ANA-MPA
EU policies on the green transition and the proposals put forward
Author: PPD TeamDate: April 27, 2026 India’s national power demand crossed 250 GW for the first time this year on April 24, 2026, reaching 2,51,771 MW at 15:45 hrs. A day later, on April 25, demand rose further to around 256.1 GW at 15:38 hrs. The peaks coincided with a heatwave, during which 19 of the world’s hottest locations were recorded in India over the same weekend. Grid operations remained stable through both days, with solar energy playing a central role in meeting daytime demand. Solar generation reached 81,539 MW at 12:15 hrs on April 24, accounting for 33.8% of total generation. At this point, thermal generation reduced to 56.3%, gas contributed 1%, and the overall fossil share declined to 57.3%. Non-fossil sources accounted for 42.7%, while wind contributed 1.6%, reflecting typical daytime patterns. By the afternoon peak at 15:45 hrs, solar output had declined to about 57,524 MW or 22.4% of generation. Thermal generation increased to 65.3%, and the fossil share rose to 66.5%. At the night peak of 2,40,240 MW recorded at 22:30 hrs, solar output was absent. Thermal generation accounted for 76.3%, hydro contributed 12.1%, gas stood at 3.5%, and wind at 4.3%. Fossil-based generation rose to 79.9%. Hydro output increased from about 9 GW at solar noon to nearly 29 GW at night, providing balancing support. The share of non-fossil generation ranged from about 20% at night to 43% during solar peak hours. This 23-percentage-point variation reflects the duck curve pattern, now evident at the national level. The pattern is visible across state-level load curves, with ongoing efforts to manage variability and extend the contribution of solar beyond daylight hours. On April 25, solar generation contributed around 57 GW, or about 22% of total generation at the time of peak demand. Around midday, solar output reached 81 GW, close to one-third of the total electricity supply. The synchronised grid demonstrated a diversity benefit of about 3% at the regional level and around 5% at the national level. This reduced coincident peak requirements and supported more efficient use of generation, reserves, and transmission capacity. India operates one of the largest synchronous grids globally under a unified frequency framework, shaped by regional demand patterns, renewable variability, and transmission flows. Solar expansion and system impact The demand records come alongside a rapid expansion in solar capacity. In 2015, India had about 4 GW of installed solar capacity. This has now crossed 150 GW, supported by additions of nearly 44–45 GW in FY2025–26. Renewable energy accounts for over 41% of total installed capacity, with solar contributing 28%. With summer demand expected to exceed 271 GW this year, solar generation will play a key role in meeting peak requirements. The pace of capacity addition is expected to average around 125 MW per day through 2030. At the same time, hydro faces increasing variability linked to climate conditions, affecting its share in the generation mix. Winter peak demand reached 245 GW in January this year, indicating a narrowing gap between seasonal peaks. This trend simplifies planning for higher renewable integration. Transmission expansion is also expected to reduce curtailment risks. Storage and the next phase of integration Battery storage is expected to support greater utilisation of solar generation by shifting daytime output to evening and night demand periods. Analysis by Ember indicates that solar combined with storage can meet a large share of demand on most days between January and April. In India, tenders for renewable energy projects with storage or peak supply obligations now account for a majority of new bids. The Union Budget has increased viability gap funding support for battery energy storage systems significantly. Solar PV generation is projected to grow at an average annual rate of 24% through 2030. As storage costs decline, similar to the cost trajectory observed in solar over the past decade, solar generation is expected to extend into hours beyond daylight. Global context These developments align with broader global trends. In 2025, renewable energy accounted for nearly 34% of global electricity generation, exceeding coal’s share for the first time in over a century. Solar contributed a significant portion of incremental demand, accounting for more than a quarter of additional global energy consumption, according to the International Energy Agency’s Global Energy Review 2026. From a marginal contributor in 2015, solar has become the fastest-growing energy source globally, with costs falling below coal in many markets. India’s recent grid performance reflects this structural shift in the energy system. The featured photograph is for representation only. Author: PPD Team Date: December 26, 2025 The Comptroller and Auditor General of India (CAG) has reported major deficiencies in the planning, execution, financial management, and monitoring of the Deen Dayal Upadhyaya Gram Jyoti Yojana (DDUGJY) and the Pradhan Mantri Sahaj Bijli Har Ghar Yojana (SAUBHAGYA). The Government of India launched the schemes to improve rural electricity access and reliability. The Deen Dayal Upadhyaya Gram Jyoti Yojana (DDUGJY) began in December 2014 to separate agricultural… Read More CAG flags planning and execution gaps in DDUGJY and SAUBHAGYA schemes Author: PPD Team Date: January 4, 2026 The Udangudi Supercritical Thermal Power Project is located in Udangudi Village, Tiruchendur Taluk, Thoothukudi District, Tamil Nadu. Originally planned as a 2×800 MW imported coal-based plant, it is now being developed as a 2×660 MW supercritical coal-based power plant by Tamil Nadu Power Generation Corporation Limited (TNPGCL). The project aims to strengthen Tamil Nadu’s power capacity while going through detailed environmental scrutiny. The project site is situated on… Read More Udangudi thermal project at a crossroads: compliance status and appraisal Author: PPD Team Date: October 26, 2025 Between January 1 and June 30, 2025, eleven utilities reported 22 cases of extra-high voltage (EHV) transmission line failures to the Standing Committee of Experts constituted by the Central Electricity Authority (CEA). These incidents involved a total of 75 towers, of which 59 were suspension-type and 16 were tension-type. Among the tension-type towers, eight were classified as “Type B,” two as “Type C,” and six as “Type D.”… Read More India records 75 EHV transmission tower failures in six months Author: PPD Team Date: June 24, 2025 India is redefining its climate policy architecture through carbon pricing, positioning itself as a key player in the global transition toward low-carbon development. With a growing economy and expanding energy demand, India is balancing decarbonisation with development. At the heart of this shift is a strategic mix of regulatory instruments, including carbon markets, voluntary credit mechanisms, and energy efficiency mandates. Together, they signal a structural transformation in… Read More India’s Carbon Market Strategy Author: PPD Team Date: September 22, 2025 A transformer works on the principle of electromagnetic induction. It transfers power from one circuit to another at the same frequency but with a change in voltage. The device has a steel core, usually laminated to reduce losses, which provides a path for magnetic flux. It has two windings: the primary, connected to the power source, and the secondary, connected to the load. Depending on how the windings… Read More Transformers: industry growth, demand drivers, and market outlook Author: PPD Team Date: October 22, 2025 The past year witnessed several leadership transitions across the power sector, both at the ministerial level and within major companies. New ministers have taken charge at the central and state levels, while several public and private sector organisations have also announced senior management appointments. Among public sector undertakings, leadership changes were seen in the Ministry of New and Renewable Energy, NTPC, Solar Energy Corporation of India (SECI), and… Read More Key leadership changes in India’s power sector Your email address will not be published.Required fields are marked *
PLEASE NOTE: A verification email will be sent to your address before you can access your trial.
Law360 may contact you in your professional capacity with information about our other products, services and events that we believe may be of interest.
You’ll be able to update your communication preferences via the unsubscribe link provided within our communications.
We take your privacy seriously. Please see our Privacy Policy.
Law360 takes your privacy seriously. Please see our Privacy Policy.
0 Powered by : Solar Energy Corporation of India (SECI), a New Delhi-based government enterprise, has issued a corrigendum for its Dhar PV loan RFP. The RFP seeks INR 660 Crores (~$72.6 million) for a 200 MW PV power project in Madhya Pradesh, India. The corrigendum, dated 24-04-2026 followed queries from prospective banks and financial institutions. SECI has revised the reset period under Sr no 7 Annexure from not less than 6 months to not less than 3 months. The bid submission deadline was extended from 24-Apr-2026 to 11-May-2026, while other RFP terms and conditions remain unchanged. The corrigendum will form an integral part of the original RFP issued for and on behalf of SECI.
Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript. Advertisement Scientific Reportsvolume 16, Article number: 10537 (2026) Cite this article 770 Accesses Metrics details In view of the significant volatility and randomness of photovoltaic power, traditional forecasting methods are unable to meet the requirements for high prediction accuracy. It is urgent to develop a prediction model with high accuracy and strong stability. Therefore, this study proposes a novel multi-step short-term photovoltaic power prediction model based on Variational Mode Decomposition (VMD), Improved Whale Migration Algorithm (IWMA), and Convolutional Neural Network-Kernel Extreme Learning Machine structure (CNN-KELM). Initially, VMD is employed to decompose the original power sequence to reduce its nonlinearity and complexity. Furthermore, we construct a CNN-KELM hybrid model, and the IWMA algorithm, which integrates chaotic mapping, dynamic inertia weight and dynamic factor adjustment with Lévy flight strategy, is introduced to optimize the model parameters, thereby enhancing the prediction performance. Moreover, for each component, a VMD-CNN-IWMA-KELM forecasting model is established, and the predicted results are reconstructed and superimposed to obtain the final prediction. Finally, the performance of the proposed model is validated using two datasets. The experimental results show that the proposed model in this paper shows significant advantages in accuracy and stability. Its goodness-of-fit values reach 96.71% and 92.33%, respectively, effectively improving the accuracy of photovoltaic power prediction. Driven by the global “carbon neutrality” goal, renewable energy has become the core force in the transformation of the energy structure1. Solar energy has the advantages of wide resource distribution, easy accessibility, high availability, and zero carbon emissions. It is one of the fastest-growing forms of renewable energy. It has now become an important direction for energy development and utilization in various countries. Photovoltaic (PV) technology, as a convenient means of utilizing solar energy, can directly convert solar energy into the most urgently needed and highly adaptable form of energy—electricity2. On the one hand, photovoltaic power generation is the most mainstream conversion pathway of solar energy. The accuracy of its power forecasting is of vital importance to the scheduling and operation of power systems. It directly affects the efficiency of optimized operation of the distribution network3. On the other hand, future population growth will drive a simultaneous increase in electricity demand, and society’s reliance on photovoltaic power generation will continue to rise4,5. Moreover, the grid-connected power generation capacity of photovoltaic energy is closely related to weather conditions and is easily constrained by weather intermittency6. As a result, solar power generation exhibits nonlinear and nonstationary characteristics, which pose significant challenges to photovoltaic power forecasting7,8,9,10,11,12,13,14. Therefore, developing a reliable photovoltaic power forecasting model that reduces noise interference and achieves accurate predictions is of significant theoretical and practical importance for promoting the widespread adoption of photovoltaic power generation and ensuring the safe, efficient, and economical operation of the entire power system. Current photovoltaic power generation forecasting methodologies are primarily categorized into three types: physical forecasting methods, statistical forecasting methods, and hybrid forecasting methods. Physical methods rely on the physical principles of photovoltaic systems to explore the relationship between power and the power generation characteristics of photovoltaic modules. For instance, literature15 adopts an equivalent circuit model to calculate the current-voltage (I-V) characteristics of photovoltaic panels, and adjusts the output voltage of the PV panels via an enhanced MPPT method to obtain photovoltaic electrical power. Ref16. proposes a Power Law Model (PLM) for photovoltaic module modeling, which dynamically updates the model using meteorological parameters. Literature17 constructs a physics-informed model using numerical weather prediction (NWP) data and obtains the expected power output through calculations, which achieves favorable performance. Although physical methods for prediction can deeply explore the physical characteristics of photovoltaic systems, when modeling with physical methods, assumptions and simplifications are required, making it difficult to accurately capture stable patterns in practical applications and thus not suitable for PV power prediction. To address the demand for short-term forecasting, statistical methods emerge. The core of this approach is to construct a mapping association between multi-variable past operational data and photovoltaic power generation by extracting correlations and change patterns from historical data, thereby achieving future power prediction. Among the common statistical prediction models are: Autoregressive Moving Average Model (ARMA)18, Autoregressive Integrated Moving Average Model (ARIMA)19, etc. In Ref20. mines data from 8 photovoltaic (PV) power plants in South Korea and conducts a performance comparison between the vector autoregressive (VAR) and the ARIMA for the prediction of hourly regional power generation. Literature21 establishes ARIMA and comparative models for predictive performance analysis, introducing a solar radiation variability index to enhance the model. The comparative study underscores the superior efficiency of the ARIMA model. However, statistical methods are heavily reliant on historical data, and their advantages may diminish when dealing with highly nonlinear behaviors, unforeseen events, or poor-quality historical datasets. Therefore, many scholars turn their attention to artificial intelligence models, such as machine learning algorithms like Support Vector Machine (SVM)22 and Extreme Learning Machine (ELM)23,24 and deep learning algorithms like Convolutional Neural Network (CNN)25 and Long Short-Term Memory Artificial Neural Network (LSTM)26,27, which have been widely used due to their robustness and high prediction accuracy. As a variant of SVM models, the Support Vector Regression (SVR) model plays a critical role in short-term photovoltaic power generation forecasting. Literature28 builds a BP model and an SVR model. It uses different evaluation metrics to compare the two models. The result shows that the SVR model has higher forecasting precision and better generalization ability when there are only a small number of samples. Literature29 develops the FWOA-SVR model, which integrates fractional calculus to enhance hyperparameter optimization, thereby improving the prediction performance of solar power generation. As a feedforward neural network, Extreme Learning Machine (ELM) features fast learning speed and strong generalization ability, and has demonstrated excellent application effects in multiple fields30. Literature31 integrates the persistence method and the ELM model by leveraging the assumption of a high correlation between the current and future values of power data. This enables the P-ELM model to not only retain the advantages of ELM but also achieve stable storage of model parameters through persistence, thereby reducing the training cost of the model. The Kernel Extreme Learning Machine (KELM) is a model improved upon the ELM by introducing kernel methods to address the issues of insufficient generalization ability and excessive dependence on the number of hidden layer nodes when the ELM handles nonlinear problems. It has better prediction accuracy and robustness. Literature32 mines the internal features of data through multi-scale similar day clustering and fast iterative filtering decomposition, then uses the KELM model for prediction, and demonstrates the model’s advantages through multi-fusion strategies. The above-mentioned physical and statistical methods enhance the forecasting precision of short-term PV power generation to a notable degree. However, due to the non-linear and non-stationary characteristics of photovoltaic data, the prediction effect for the segments with strong fluctuations is still not satisfactory. Therefore, seeking effective data processing and feature extraction methods to alleviate noise interference and improve data quality becomes a focus of attention. Researchers introduced signal processing methods to convert power signals into components with periodic characteristics, providing the model with higher-quality feature inputs. Widely adopted signal processing approaches involve wavelet transform (WT)33, empirical mode decomposition (EMD)34, and variational mode decomposition (VMD)35, etc. Literature36 proposes a novel power generation data prediction method based on Wavelet Transform (WT) and adaptive hybrid optimization, which not only effectively mitigates noise interference but also enhances feature extraction capability. Literature34 proposes a dual decomposition model combining time-varying filtering and empirical mode decomposition (TVF-EMD), which can effectively alleviate the volatility of photovoltaic power and thereby improve the prediction accuracy of the model. WT and EMD can both break down the original waveform to make prediction results better. But they still have some limitations. The WT model has poor robustness, while EMD may have endpoint effects and over-enveloping problems in some situations. In contrast, VMD model can effectively solve the mode aliasing problem existing in EMD. This model not only has stronger anti-interference ability, but also can effectively reduce the impact of endpoint effects. Literature37 integrates the VMD and KELM models to predict photovoltaic output under major extreme weather conditions. It is verified through four different extreme weather conditions that the combination with signal methods can enhance the adaptability of the model to extreme conditions. Signal decomposition methods can reduce the difficulty of predicting power signals affected by noise. But these methods still have some limits when extracting useful features. Convolutional neural networks (CNN), with their unique network structure, can effectively capture local correlations and hierarchical features in data, and perform exceptionally well in improving parameter efficiency and model robustness. Combining CNN with other predictive models can make up for the deficiency of traditional methods in learning sequence patterns. For example, in Ref38., CNN is respectively combined with Bi-LSTM, Transformer structures, and multi-layer perceptions (MLP). Experiments demonstrate that the two hybrid models outperform the single baseline model in prediction tasks at the daily, weekly, and monthly scales. Literature39 combines VMD, CNN, the IPSO algorithm, and the LSSVM. By using VMD to decompose photovoltaic electrical data into a series of intrinsic mode functions (IMFs), the capacity for extracting the temporal-frequency characteristics of the signals is significantly improved. Based on the above analysis, integrating data processing methods with prediction models to construct hybrid models becomes the main trend in recent studies on PV power prediction. The Kernel Extreme Learning Machine (KELM), due to its strong nonlinear fitting ability and high computational efficiency, demonstrates an excellent adaptability to the task of photovoltaic electrical output forecasting. However, its predictive accuracy and generalization ability largely relies on the selection of hyperparameters. Therefore, most studies adopt heuristic optimization algorithms to optimize the hyperparameters of the KELM model. Literature40 employs the Improved Dung Beetle Optimization (IDBO) algorithm, literature41 adopts the Improved Moth-Flame Optimization (IMFO) algorithm, etc. These algorithms automatically determine the selection of hyperparameters through their own excellent optimization capabilities, solving the problem that manual parameter tuning struggles to balance underfitting and overfitting, and ultimately improving the prediction accuracy. A whale migration algorithm (WMA) proposed in Literature42 effectively balances the global exploration and local exploitation processes by integrating the leader-follower mechanism with an adaptive migration strategy, demonstrating superior optimization capability compared to traditional algorithms. Therefore, this paper will improve the WMA algorithm to enhance the model’s requirements for parameter optimization. Based on the relevant models and specific methods discussed in the literature review and Table 1, current photovoltaic short-term power forecasting has established a mainstream framework and improved performance through technological integration. However, existing research still faces significant limitations in addressing core issues such as data nonlinearity and non-stationarity:The adaptability and predictive accuracy of both single-model forecasting and traditional hybrid models still exhibit shortcomings. The adaptability and predictive accuracy of both single-model forecasting and traditional hybrid models still exhibit shortcomings. Physical methods are not suitable for short-term forecasting, and traditional statistical methods are constrained by the quality of historical data. Single and simple hybrid models have limitations and cannot extract features in depth. Traditional KELM hyperparameter tuning struggles to balance global and local optimization. The above shortcomings limit the prediction accuracy. This paper constructs a hybrid VMD-CNN-IWMA-KELM model. By employing VMD for denoising and CNN-KELM for deep feature extraction and fitting, the model’s adaptability and prediction accuracy are enhanced. The performance of heuristic optimization algorithms in model hyperparameter tuning requires improvement. Existing heuristic algorithms for optimizing KELM hyperparameters suffer from slow convergence, low accuracy, susceptibility to local optima, and poor stability, making them ill-suited for complex photovoltaic data. This paper proposes the IWMA algorithm, which employs chaotic mapping, dynamic inertial weighting, and dynamic factor-adjustd Lévy flight to optimize CNN-KELM hyperparameters. This approach avoids manual intervention and maximizes the model’s predictive potential. Existing mixed models lack comprehensive validity verification and targeted analysis. The current hybrid model validation lacks systematic rigor, featuring insufficient comparative models and inadequate assessment of generalization capabilities and robustness. The absence of ablation studies and complexity analysis hinders practical engineering applications. Based on actual datasets from two power plants, this paper establishes nine comparative models. Through multi-indicator analysis, ablation experiments, and complexity analysis, it comprehensively validates the superiority of the proposed model across multiple dimensions, providing robust support for engineering applications. In summary, existing research exhibits gaps in feature extraction, model adaptability, hyperparameter tuning, and effectiveness validation. This paper addresses the aforementioned issues by constructing hybrid models, improving optimization algorithms, and conducting comprehensive validation, thereby enhancing the accuracy and robustness of short-term photovoltaic power forecasting. To further boost the accuracy of PV power prediction, this study improves the WMA algorithm by introducing chaotic mapping, dynamic inertia weight, and flight strategy based on dynamic factor adjustment, forming the Improved Whale Migration Algorithm (IWMA). Compared with the WMA algorithm, the IWMA is enhanced in terms of convergent precision, rate of convergence, and the local optima avoidance capability. To address the volatility of the photovoltaic power series, Variational Mode Decomposition (VMD) is employed to decompose the sequence, thereby mitigating the influence of noise. Then, a CNN-KELM hybrid model is constructed to enhance the model’s feature extraction capability. Subsequently, the IWMA algorithm is used to optimize the hyperparameters of the CNN-KELM model, aiming to effectively enhance the model’s fitting ability and generalization performance. Therefore, this paper constructs a hybrid CNN-KELM forecasting model optimized by VMD and IWMA. Compared to the single KELM model, the proposed model in this paper demonstrates higher prediction accuracy and greater stability in short-term photovoltaic power forecasting tasks. The main contributions and novelties are summarized as follows: By introducing chaotic mapping, dynamic inertia weight and a dynamic factor-adjusted Lévy flight strategy, an Improved Whale Migration Algorithm (IWMA) is proposed to enhance the algorithm’s exploration and exploitation capabilities, thereby improving the optimization efficiency. To obtain an improved prediction model, a CNN-KELM hybrid prediction model is constructed, and the hyperparameters of the hybrid model are optimized using the IWMA algorithm, thereby enhancing the prediction accuracy of the model. A photovoltaic power prediction model constructed on VMD-CNN-IWMA-KELM is established. By using the VMD signal decomposition method, the instability of the original power data is mitigated, providing higher-quality input data for the model and thereby enhancing the prediction accuracy of the model. Nine comparative models are selected to conduct multiple sets of simulation experiments on the actual data set of a power plant in China. The effectiveness of the proposed model is verified from multiple perspectives, including true-predicted curve comparison, linear regression, model evaluation index, ablation experiment and model complexity analysis. This paper has six parts, and the main content of the subsequent parts is arranged as follows: The “Methodology” part explains the basic theories behind VMD, CNN, KELM and the CNN-KELM structure; The “Improved Whale Migration Algorithm” part presents the basic theory of WMA and conducts evaluation experiments on the improvement strategies and performance of the IWMA; The “Prediction of PV power generation based on VMD-CNN-IWMA-KELM” part presents the IWMA-optimized CNN-KELM model and the VMD-CNN-IWAM-KELM photovoltaic power generation power prediction model, and introduces the prediction process; The “Experimental design” part describes the specific details of the experiments as well as the software and solvers used to conduct them; The “Results and analysis of the experiment”part presents the relevant experimental analysis. The “Conclusion” part sums up the whole paper with key findings and extends the model; The “Research limitations” part discusses the limitations of the study and future work. Variational Mode Decomposition (VMD)43 is an adaptive signal processing method, and it does not use recursion. By iteratively searching the optimal solution of the variational model, the center frequency and bandwidth of each IMF are adaptively determined, and the corresponding modes are estimated, so as to properly balance the error between the modes, so as to realize the effective separation of the signal frequency domain components. By appropriately balancing the errors among modes, it achieves effective separation of the signal’s frequency-domain components. When compared with the classical empirical mode decomposition, VMD can effectively alleviate the modal aliasing effect. The definition of the IMF is as follows: where, ({A_k}left( t right)) denotes the envelope assignment, and ({varphi _k}left( t right)) represents the instantaneous phase. In fact, the specific implementation process of VMD decomposition is to transform the constrained variational problem into an unconstrained variational problem for solution. The decomposition problem of any signal can be described by Eq. (2). In Eq. (2), ({u_k}=left{ {{u_1},{u_2}, cdot cdot cdot {u_k}} right}) denotes the k-th modal component function, and ({omega _k}=left{ {{omega _1},{omega _2}, cdot cdot cdot {omega _k}} right}) stands for the center frequency of the k-th modal mode. (*) stands for the operator symbol for convolution. (delta left( t right)) is the Dirac delta function, “s.t.” indicates the constraint condition, and (fleft( t right)) denotes the initial input data. Through the introduction of a quadratic penalty term (theta) and Lagrangian multiplier (lambda left( t right)) into Eq. (1), the restricted formulation is transformed into an un restricted one through the method of Lagrange multipliers (LMM) and the Alternating Direction Method of Multipliers (ADMM), thereby converting Eq. (2) into Eq. (3). where, (L({text{ }} cdot {text{ }})) represents the Lagrangian function, (alpha) denotes the penalty factor, and (lambda left( t right)) signifies the Lagrange multiplier. The Convolutional Neural Network (CNN)44 is a deep learning model motivated by the structure of the biological visual cortex. Its core is to extract local features of data and realize feature hierarchical abstraction through convolution operation, weight sharing and pooling operation, which can be widely used in data processing and analysis. One-dimensional Convolutional Neural Network (1D CNN)45 is an important variant of Convolu-tional Neural Network (CNN) and is a type of model specifically designed for processing sequential data. Its structure typically consists of an input layer, a convolutional layer, an activation function, a pooling layer, and an output layer. The data in the input layer is processed by the convolutional kernel through its receptive field to complete feature extraction and mapping. We can express this process as: In Eq. (4), (a_{j}^{l}) denotes the convolution output data, and (a_{i}^{{l – 1}}) represents the previous convolution input feature data. (k_{j}^{l}) is the convolution kernel, (b_{j}^{l}) denotes the bias parameter, (x( * )) is the activation. To introduce nonlinearity into the network, we use the piecewise linear ReLU function as the activation function, with its expression given below: The pooling layer filters the convolutional feature data according to Eq. (6) and constructs the feature sequence. The output layer corresponds to the target variable, and the CNN structure is illustrated in Fig. 1. Structure diagram of 1DCNN. Kernel Extreme Learning Machine (KELM)46 is a machine learning model developed by integrating the kernel technique into the conventional Extreme Learning Machine (ELM). It retains the high efficiency of ELM while using a kernel function to overcome the issue of output fluctuations caused by random initialization in ELM, thereby demonstrating superior learning ability and generalization capability. The kernel matrix of KELM is defined based on Mercer’s condition, with its expression presented below: where, ({H^T}) denotes the Moore-Penrose inverse of H, ({x_i}) and ({x_j}) are the input values of the samples, (Kleft( {{x_i},{x_j}} right)) is the kernel function. Considering the fitting ability and robustness of the comprehensive model, this paper selects the Gaussian kernel function, which has fewer parameters and stronger universality, as its kernel function. Its expression is: In Eq. (8), (delta) denotes the kernel parameter. After ELM incorporates the above kernel function matrix, the model output of KELM is: where, I denotes the identity matrix, which is used to preserve matrix structure. (lambda) is the regularization coefficient, (hleft( x right)) represents the hidden-layer feature mapping, (fleft( x right)) is the model’s output term. The specific network structure of KELM is illustrated in Fig. 2. Kernel extreme learning machine structure diagram. In Fig. 2, ({x_i}) denotes the input variable, ({y_i}) the output variable, while ({a_{ij}}) and ({v_{ij}}) stand for the connection weights between the i-th neuron and the j-th neuron in different layers. CNN-KELM is a hybrid deep learning model that combines the strengths of 1D CNN and KELM. The structure selection is based on the core requirements of photovoltaic power prediction, taking into account both the accuracy of feature extraction and the efficiency of prediction. Compared with the common CNN-LSTM, CNN-GRU, and Transformer-based structures, although they can capture temporal dependencies, they have the drawbacks of numerous training parameters, slow convergence, high risk of overfitting, and high requirements for computing power. The combination of CNN and KELM can effectively remedy the above deficiency. The CNN-KELM model first uses the convolutional and pooling layers of 1D CNN to complete the extraction of core features. Among them, the convolutional layer extracts local temporal characteristics by sliding the convolution kernel across the series data. Pooling layers perform down-sampling on the convolved features, reducing data redundancy while enhancing the model’s robustness against minor signal variations. The 1D CNN model processes the original signal. It turns the signal into a representative set of feature vector. KELM demonstrates excellent applicability in multi-step prediction. It maps the low-dimensional features to a high-dimensional space through a kernel function to solve nonlinear regression problems. Then, the extracted feature vectors are directly input into the KELM. Compared with models such as LSTM and GRU, KELM requires no complex iterative training with higher computational efficiency. At the same time, its structure is simple and the parameters have low redundancy. It can effectively reduce the cumulative error in multi-step prediction, and improve the generalization ability and prediction stability of the model. In addition, KELM does not require a large number of samples for support and is suitable for the sample scenario of this study. It can make up for the drawbacks of long training time and insufficient generalization ability in traditional deep learning models. The integration of CNN and KELM enables the collaborative optimization from automatic feature learning to efficient and accurate prediction. The Whale Migration Algorithm (WMA)42 is a meta-heuristic optimization algorithm that simulates the collaborative migration behavior of humpback whale populations. This algorithm classifies humpback whales into two distinct groups: experienced leader whales and inexperienced follower whales (or calves). It achieves a balance between global exploration and local exploitation by simulating the collective coordination and social interaction behaviors of whale groups during migration. The WMA algorithm incorporates the leader-follower mechanism and adaptive migration strategy. These two components work in tandem to establish an efficient mathematical model for problem-solving. Compared with the Whale Optimization Algorithm (WOA), although both are inspired by whale behavior, WOA focuses on the bubble-net foraging mechanism, featuring strong local exploitation but weak global exploration, whereas WMA emphasizes population migration and delivers superior stability in global search. Compared with classic algorithms such as Particle Swarm Optimization (PSO) and Grey Wolf Optimizer (GWO), WMA circumvents the problems of high computational complexity and longtime consumption via its dual mechanisms, featuring a simpler iterative mechanism and more stable structure. The algorithm starts by creating search agents. It sets their evolutionary direction clearly. The population then optimizes step by step along this direction. Specifically, WMA simulates the initial distribution of the whale population by randomly generating an initial population within the defined search space, where each individual’s position is expressed as: where, L and U are the search space’s lower and upper bounds. ({text{rand }}(1,D)) is a D-dimensional random vector generated within the interval [0,1], and “(odot)” denotes the Hadamard product of two vectors. Furthermore, the algorithm sorts all population individuals in descending order of fitness. The individual with the highest fitness is marked as ({X_1}), which is the current optimal solution ({X_{Best}}). The sorted population can be expressed by formula (11). In the WMA algorithm, the leader refers to the individual in the population that is more experienced, has a better position, and achieves a higher fitness. Half the population size (({N_{pop}})) is designated as the number of leading whales (({N_L})). To characterize the overall position of the whale pod during migration, the average value ({X_{Mean}}) of all leaders’ positions is calculated, which reflects the concentration trend of the population within the current search domain. The calculation formula is as follows: Assuming the objective function value is analogous to the age of a whale, each juvenile whale emulates and follows the individual in the population whose “age” most closely approximates its own. For instance, the movement of individual whale ({X_i}(i={N_L}+1, cdot cdot cdot ,{N_{pop}})) within the whale group is influenced by the nearest whale ({X_{i – 1}}) that is ranked higher in terms of fitness, and the degree of influence is quantified by ({text{rand }}(1,D) odot ({X_{i – 1}} – {X_i})). If the distance between ({X_{Mean}}) and ({X_{Best}}) gradually shortens, it indicates that the leader population is approaching ({X_{Best}}). At the same time, the less-experienced whale must also move synchronously in the direction of ({text{rand }}(1,D) odot ({X_{Best}} – {X_{Mean}})). If the objective function value of the new position is superior, that is, when the condition (f(X_{i}^{{new}})) < (f({X_i})) is satisfied, the algorithm updates the position of the calf whale. The position update Equation for the i-th young whale is as follows: During whale migration, the leader draws upon its experience to identify and select the optimal route. If the objective function value at the new position is superior, i.e., when the specified condition (f(X_{i}^{{new}}) ) < (f({X_i})) is met, the algorithm updates the position of the i-th leader whale using formula (15). where, ({r_1}) and ({r_2}) are D-dimensional random vectors, L is the lower bound vector of position, (U – L) specifies the search direction and range. The algorithm sorts the entire whale population by fitness from best to worst, then selects the top ({N_L}) optimal individuals as leaders for the next generation. This paper addresses the shortcomings of the Whale Migration Algorithm (WMA), such as the unsatisfactory initial solution quality, low convergence accuracy, and weak global and local search capabilities, and proposes three improvement strategies to comprehensively enhance the optimization ability of the algorithm. Initially, we introduce the Tent chaotic map for initial population generation, leveraging its uniform distribution properties to enhance solution quality. Secondly, dynamic inertia weights are introduced in the global search stage to expedite convergence and enhance search precision. Finally, the Lévy flight strategy with dynamically adjusted factors is incorporated into the calves’ position update to boost the algorithm’s capacity to break free from local optima. Through the three strategies mentioned above, we propose the Improved Whale Migration Algorithm (IWMA). The quality of the initial population directly determines the algorithm’s exploration capability and convergence rate. The more evenly the initial solutions are distributed across the search domain, the greater the likelihood that the algorithm will locate the global optimal solution. As stated in Ref47., chaotic maps generate random sequences via deterministic systems. Due to their high sensitivity to initial conditions, these maps produce significantly different outputs, a characteristic that can be leveraged to improve population diversity in optimization algorithms. This paper selects the Tent chaotic function for population initialization because of its superior uniform distribution and good ergodicity, which helps to generate more comprehensive initial solutions within the search domain and thereby improve the global exploration ability48. Its specific expression is: where, (beta) is a positive real number defined on the interval (0,1). Extensive experiments show that the system exhibits optimal chaotic characteristics when (beta =0.4999.)(X_{i}^{{New}}) is a function of (X(X in [0,1])) with parameter (beta). The distribution of Tent chaotic mapping in the solution space is shown in Fig. 3. Its point distribution and numerical frequency both exhibit excellent uniformity, meeting the requirements for enhancing initial population quality. Chaotic mapping spatial distribution diagram. Balancing global exploration and local exploitation is a core element in enhancing the optimization accuracy and convergence speed of meta-heuristic algorithms. It is indicated in Literature49 that a larger inertia weight value corresponds to stronger global exploration capability, while a smaller inertia weight value corresponds to stronger local search capability. To resolve the limitations of slow convergence speed and low precision during the early iterations of the WMA algorithm, this paper introduces the dynamic inertia weight factor adopted in Ref50. into the position updating formula of the leader whale in the WMA algorithm. This factor incorporates a nonlinear decreasing mechanism allowing the algorithm to perform extensive global exploration in the early iterations and gradually concentrate on local search regions in the later stages. Thus, while enhancing the convergence speed, premature convergence can be effectively avoided. Its expression is as follows: where, t and T denote the current iteration number and the maximum number of iterations, respectively. ({w_{hbox{max} }}=0.9,{mkern 1mu})and ({w_{hbox{min} }}=0.2). Additionally, we introduce a random term (rand) to the inertia weight, giving it a certain randomness in each iteration. This randomness helps improve the algorithm’s ability to escape local optimal solutions. To address the limitation of the original WMA algorithm, which relies solely on the leader whale’s own position and random terms for updates during the early exploration phase. In this paper, we introduce a position update mechanism, which integrates individual and group experience, by introducing the global optimal position ({X_{Best}}), the average position of the population ({X_{Mean}}), and the dynamic inertia weight factor. This mechanism strengthens information exchange and guides the population to collaboratively search for the optimal solution. During the iterative process, if condition (f(X_{i}^{{new}})) < (f({X_i})) is satisfied, the position of the i-th leading whale is updated according to Eq. (18). where, ({X_i}) denotes the current position, ({X_{Mean}}) represents the average of the leading whales, and ({X_{Best}}) refers to the current global optimal solution. Then, perform boundary constraint processing on the updated position. where, (X_{{i2}}^{{New}}) represents the position after boundary processing of (X_{i}^{{{text{new}}}}). In the WMA algorithm, the position updating of the juvenile whale depends on the average location and the position of the neighboring whale. If either type of whale performs poorly, the juvenile whales will deviate from the population. This deviation reduces population diversity, which in turn weakens the algorithm’s overall optimization capability. To overcome this limitation, this paper introduces a Lévy flight strategy with dynamic factor adjustment to improve the position update mechanism of young whales, enhancing both search efficiency and stability. Lévy flight, as a random walk pattern, has step lengths that follow a heavy-tailed distribution51. Compared with Gaussian walk, it can generate larger step lengths with a certain probability, which enables individuals break away from local optima solutions and expand the search scope. Its random path satisfies: In practical applications, the Mantegna algorithm is often used to generate Lévy steps, and the specific calculation formula is: where, (mu) and (nu) follow a normal distribution: where, ({delta _u}) and ({delta _v}) are respectively: where, (beta) is usually taken as 1.5. In traditional Lévy flight, the step length parameter (alpha) is usually a fixed value, which limits the flexibility of the search. Accordingly, this study introduces a dynamic factor adjustment strategy that enables adaptive variation of (alpha) throughout the iterative process. When the population diversity decreases, increasing (alpha) can enhance the exploration intensity and prevent premature convergence. This paper adopts the Sigmoid function to control the attenuation process of (alpha), with its specific mathematical expression formulated as follows: where, (z=t/T) represents the normalized iterative process. (alpha) is the initial step size. Set the constant(k=0.05). When the condition (f(X_{i}^{{new}})) < ( f({X_i})) is satisfied, then the position update formula for the i-th less-experienced whale is adjusted as follows: where, ({X_{i – 1}}) represents the position of the previous whale, and ({X_i}) denotes the current position of the whale. The symbol (otimes) stands for the dot product, while (alpha) is defined by Eq. (24). Subsequently, boundary constraint processing is applied to the updated positions. where, (X_{{i2}}^{{New}}) represents the position after boundary processing of (X_{i}^{{{text{new}}}}). Compared to the original WMA, IWMA retains its core mechanism while introducing a chaotic mapping, dynamic inertial weighting, and a Lévy flight strategy with dynamic factor adjustment. This addresses the shortcomings of WMA’s fixed parameters, such as slow convergence and difficulty escaping local optima. It enhances optimization efficiency and precision. Moreover, all the newly added hyperparameters of the IWMA are parameters with clear physical meanings and fixed value ranges, requiring no additional tuning. Compared with the no-hyperparameter design of the standard WMA, it only introduces a small number of new parameters without the need for complex debugging, balancing algorithm performance and ease of use. This makes the IWMA algorithm better suited to meet the hyperparameter optimization requirements of models in photovoltaic power forecasting. Pseudo-code of the proposed IWMA. Suppose the population quantity denoted as ({N_{pop}}), the uppermost limit of iterations is (MaxIt), and the dimensionality of the problem is D. The time complexity of the IWMA algorithm primarily stems from two components: population initialization and iterative update. The complexity of the original WMA algorithm across all iterations is (O({N_{pop}} times D times MaxIt)). At the initial phase, the IWMA algorithm exhibits the same time complexity as the WMA algorithm, both being (O({N_{pop}} times D)). Throughout the iteration steps, IWMA introduces a dynamic inertia weight and a dynamic factor-adjusted Lévy flight strategy. Both the exploration phase and the exploitation phase share an identical time complexity of (O({N_{pop}}/2 times D)). Since each stage performs (MaxIt) iterations, the IWMA algorithm’s total time complexity stays(O({N_{pop}} times D times MaxIt)). Therefore, by implementing enhanced strategies and structural enhancements, the IWMA algorithm boosts its performance, all the while preserving a similar time complexity level to that of the original algorithm. To validate the comprehensive optimization ability of the IWMA algorithm after introducing the optimization strategies, this paper selects the WMA algorithm and six newly proposed intelligent optimization algorithms as comparison algorithms, including the Butterfly Optimization Algorithm (BOA)52, the Whale Optimization Algorithm (WOA)53, the Greylag Goose Optimization (GGO)54, the Dung Beetle Optimizer (DBO)55 and the Parrot Optimizer (PO)56. The experiment employs eleven benchmark test functions for performance evaluation. Among them, functions F1 to F5 are unimodal functions with a single global optimum, which are utilized to evaluate the rate of convergence and convergence accuracy of the algorithm during the iterative process. Functions F6 to F9 are multimodal and have numerous local optimal solutions. They can serve as a basis for evaluating the algorithm’s ability to avoid getting trapped in local optima. Functions F10 to F11 are the fixed-dimension multimodal functions, and they can be employed to further assess the algorithm’s robustness within intricate high-dimensional spaces. Table 2 details the mathematical definitions, search spaces, dimensions, and ideal values of 11 test functions. In order to ensure fairness in the experimental procedure and comparability of the results, we uniformly set the population quantity of all algorithms to 30 and define the maximum number of iterations as 1000. We independently conduct 30 runs of the experiments on each of the eleven test functions, and then record the average value (Avg) and standard deviation (Std) obtained from these 30 runs. The average value indicates the optimization accuracy of the algorithm. The closer this value is to the ideal optimum; the superior the algorithm’s search capability will be. Standard deviation is a metric to measure an algorithm’s robustness. A smaller value means the algorithm is more stable. The detailed parameter settings of other algorithms are presented in Table 3. All experiments are conducted on a 64-bit Windows 10 system with an Intel(R) Core (TM) i5-10500 CPU @ 3.10 GHz processor, and all algorithms are implemented using MATLAB 2024a. The best results obtained in this paper are shown in bold. The specific experimental outcomes are exhibited in Table 4. As presented in Table 4, we can observe that the IWMA algorithm demonstrates superior compared to the other algorithms in overall performance. Especially in multiple test functions, the average value and standard deviation of this algorithm are close to the theoretical optimal values, demonstrating outstanding optimization ability. On unimodal test functions, the IWMA algorithm is significantly superior to comparison algorithms for convergence accuracy and standard deviation. For instance, for F4, the mean value of the IWMA algorithm is 7.62 × 10–149, which is 149 orders of magnitude higher than that of the original WMA algorithm. Although it does not attain the theoretical optimal value in certain test functions, its solution accuracy and error are still markedly superior to those of other algorithms. Among the multimodal test functions, the IWMA algorithm achieves the superior performance in many metrics for some functions. This means the changes we made help the algorithm get away from local optima easily and make it more robust. On fixed-dimension multimodal functions, the mean value of IWMA is closest to the theoretical best optimum, and its standard deviation also performs well. Although GGO has a slightly smaller standard deviation on the F6 function, the IWMA maintains a comparable magnitude with negligible discrepancy. Furthermore, taking the F11 test function as an example, the mean of IWMA is −1.01 × 10¹. This value is very close to the theoretical optimum of −10. Also, its standard deviation is 1.51 × 10⁻¹, which is the smallest among all algorithms. So, we can see that IWMA has excellent search ability and stability when dealing with high-dimensional complex problems. Overall, the IWMA algorithm demonstrates outstanding performance across all benchmark functions. In this paper, we simulate the convergence of seven algorithms to different test functions. The convergence curves are presented in Fig. 4. Among the unimodal functions shown in Fig. 4(a) to (e), the IWMA algorithm consistently maintains the strengths of fast convergence speed and high precision throughout the entire iterative process, outperforming other algorithms. Among the multimodal and fixed-dimensional multimodal functions illustrated in Fig. 4(f) to (k), the IWMA algorithm can rapidly approach the optimal solution within a relatively small number of iterations, achieving the best convergence efficiency. In particular, in Fig. 4(h) and (k), the IWMA algorithm can achieve the optimal fitness value at the very beginning and exhibits a high-precision convergence state. The experimental results demonstrate that IWMA has good adaptability and convergence for different types of test functions, and can avoid local optimal solutions, enabling it to approach the global optimal value quickly and stably. In this way, the effectiveness of the improved strategies and structural optimization introduced in this study for enhancing the algorithm’s search-optimization ability is verified. Current photovoltaic power forecasting methodologies require further improvement in their adaptability to variable meteorological conditions and complex geographical environments. In short-term forecasting, the VMD model enhances prediction accuracy and model robustness by decomposing photovoltaic power sequences into multiple sub-sequences with distinct characteristics and relative stationarity. The CNN-KELM hybrid model can perform deep feature extraction from data, effectively capturing the nonlinear variations in photovoltaic power output. Furthermore, the IWMA algorithm leverages its superior global search capability and high-precision convergence properties to facilitate further enhancement of the model’s predictive performance. On the basis of above analysis, this paper constructs a short-term photovoltaic power prediction model that integrates the VMD model, IWMA, and the CNN-KELM hybrid model, aiming to comprehensively enhance the model’s forecasting performance. Convergence curve of the test function for the algorithm. In the CNN-KELM hybrid model, the settings of the kernel parameter (delta) and the regularization coefficient C of KELM directly affects its prediction performance57. So, hyperparameter optimization is particularly crucial. This paper introduces the IWMA algorithm to optimize the hyperparameters of the CNN-KELM hybrid model. The goal is to make the model’s prediction accuracy better. Here is the detailed optimization procedure: Step 1. Divide the original PV power signal into training and testing sets, and do normalization processing. Step 2. Set the population size and maximum iteration of the IWMA algorithm, and set the search range for kernel parameters and regularization coefficients. Step 3. Initialize the CNN-KELM model, input the parameters of each individual in the population into the model for training and prediction, and use the root mean square error (RMSE) as the objective function to evaluate the performance of each parameter combination of the model. The RMSE is calculated using the following formula: where, n denotes the total sample size, ({y_i}) denotes the true value of the i-th sample, and ({hat {y}_i}) denotes the predicted value of the model. The algorithm performs iterative optimization with the objective of minimizing the RMSE value of the output combination parameters, with a theoretical optimal value of 0. Step 4. Update the fitness values in each iteration. If the algorithm finds a superior solution, update the population positions and fitness values, and record the current optimal kernel parameters and regularization coefficients. Step 5. Check whether the iteration count has hit the predefined maximum. If it has, bring the iteration process to an end and present the result; if not, continue carrying out the search. Step 6. Input the training dataset and the test dataset into the optimized CNN-KELM model, complete the training and output the prediction results. Based on the above process, the process of IWMA optimizing the hyperparameters of the CNN-KELM hybrid model is shown in Fig. 5. Flowchart of IWMA optimized CNN-KELM model. External environmental factors have a substantial impact on photovoltaic power generation, leading to large data fluctuations and poor stability, which restricts the performance of prediction models. Therefore, this paper introduces a multi-step prediction model of VMD-CNN-IWMA-KELM to strengthen the forecasting precision and generalization ability. This model first filters out noise through VMD decomposition, extracts the periodic characteristics of signals in different frequency bands, and improves the quality of input data. The detailed procedure of VMD decomposition is presented in Fig. 6 Subsequently, deep feature mining and selection are performed using CNN-KELM to enhance feature representation capabilities. Furthermore, the IWMA is introduced to optimize the hyperparameters of the CNN-KELM hybrid model, thereby overcoming the constraints imposed by manual parameter tuning on model performance. The specific steps for the prediction of the VMD-CNN-IWMA-KELM model are as follows: Step 1. Collect the original photovoltaic power data and meteorological data. Step 2. Break down the original photovoltaic power into multiple relatively stable IMFs through VMD, and normalize each component to eliminate the influence of dimensions. Step 3. Establish an independent CNN-KELM hybrid model for each component. Step 4. Utilize the IWMA to optimize the (delta) and C of the CNN-KELM models corresponding to each subsequence, respectively. Upon meeting the termination condition, the optimal prediction models for each component are obtained. Step 5. By superimposing the prediction outcomes of each component, the final photovoltaic power prediction value is generated. In this model, each sub model takes historical meteorological data and historical power data as inputs, producing multi-step forecast values for corresponding components as outputs. This approach does not rely on previous forecast results, enabling direct prediction. The core advantage of this strategy lies in avoiding the propagation of errors from recursive predictions. Each step’s prediction independently relies on historical input features, eliminating the cumulative risk of prior step errors influencing subsequent steps. The flow diagram of the VMD-CNN-IWMA-KELM is illustrated in Fig. 7. VMD decomposition structure diagram. This study uses solar energy data from a renewable energy generation forecasting competition provided by a regional power supply company of the State Grid Corporation of China. Two sets of 30-day data are selected from the datasets of two power stations as the experimental subjects. The two power stations are designated as Dataset A and Dataset B, with rated capacities of 50 MW and 35 MW, respectively. The time ranges are from February 10, 2019, to March 11, 2019, and from August 1, 2020, to August 30, 2020, respectively. These periods cover both winter and summer seasons, fully reflecting the impact of different seasonal meteorological conditions on photovoltaic power output and exhibiting strong representativeness. Considering that effective solar radiation mainly occurs between 8:00 and 20:00 and that photovoltaic modules generate negligible power outside this period, only data from this period are selected for analysis. With a sampling interval of 15 min, each day contains 49 samples, yielding a total of 1,470 samples over 30 days. The simulation experiment divides the data using a chronological split, with the first 24 days used as the training set and the last 6 days as the prediction set. The data file is in CSV format with GBK encoding. The input data include meteorological variables such as total solar irradiance (W/m²), direct normal irradiance (W/m²), global horizontal irradiance (W/m²), air temperature (°C), atmospheric pressure (hpa), and relative humidity (%), while the output is the photovoltaic power (MW). The power variation trends of Dataset A and Dataset B are presented in Fig. 8. It shows that the photovoltaic power data, on the basis of its periodic characteristics, also exhibits certain non-stationary and fluctuating features. Among them, Dataset B exhibits a greater degree of fluctuation and is suitable for validating the robustness of the model. To characterize the original power sequence in detail, its specific characteristics are displayed in Table 5. Although the training and test datasets differ in sample size, their maximum values, means, and standard deviations are generally comparable, indicating that the training and test datasets exhibit good statistical consistency in their characteristics. This allows the patterns learned by the model during training to be more easily applied to the test set, thereby reducing overfitting and making the prediction results more reliable. Flow chart of photovoltaic power generation forecasting model. Original photovoltaic power sequence (a) Dataset A; (b) Dataset B. To provide a unified comparison scale for data of different magnitudes and units, prevent the analysis results from being dominated by the dimensional differences of individual variables, and ensure the objectivity of the experimental conclusions, all data need to be normalized. The specific normalization operation is as follows: where, (x^{prime}) is the normalized data, ({x_{hbox{max} }}) and ({x_{hbox{min} }}) are respectively the maximum and minimum values of the original input variables, x is the original input data. In this study, we carry out the simulation experiments using an Intel (R) Core (TM) i5-10500 CPU processor with a clock speed of 3.10 GHz. The programming software used is MATLAB 2024a, and the drawing tools are MATLAB and VISIO. The parameter settings for each model are detailed in Table 6. To mitigate the randomness and volatility present in the data, this paper employs the Variational Mode Decomposition (VMD) method to process the initial photovoltaic power signals in the dataset. By converting the photovoltaic power data into multiple stationary single-frequency IMFs, the fluctuation patterns of the original data are simplified, providing more distinguishable input features for subsequent prediction models. Taking Dataset B as an example, for the two important parameters in VMD, namely the number of mode components K and the penalty factor (alpha), the proposed IWMA algorithm is employed to automatically determine their optimal values. The maximum number of iterations and population size of the algorithm are set to 30 and 15, respectively. The optimization range for the mode number K is [2, 15], and for the penalty factor (alpha) is [200, 6000]. The variation of the algorithm’s best fitness value (RMSE) during the iteration process is shown in the Fig. 9. The algorithm converges at the 20th generation, with the output parameter combination [(alpha), K] = [10, 1500]. Convergence Curve of VMD Parameter Optimization. To verify the strong robustness of the parameter combination optimized by IWMA, parameter perturbation experiments are designed in this study for validation. Taking the optimized optimal parameters as the baseline, different offset values are set around them to compare the variations in forecasting performance. The specific experimental design and results are presented in Table 7. It can be observed that when the parameter combination is [10, 1500], the corresponding RMSE value is the smallest. Therefore, the parameter selection is reasonable. This sensitivity analysis experiment verifies that the parameter combination optimized by the IWMA algorithm exhibits strong robustness. The two groups of photovoltaic power sequences are decomposed into 10 IMFs using Variational Mode Decomposition (VMD), and the decomposition results are shown in Fig. 10. We can see that each component has an inconsistent frequency but exhibits certain regularity and periodicity. By decomposition, the local features of power data can be presented more clearly. This way, it becomes easier for the model to make predictions. To verify the feasibility of the VMD-CNN-IWNA-KELM hybrid model proposed in this study, we compare the prediction results of each model with the actual photovoltaic power values and calculate multiple evaluation metrics for verification. VMD model decomposition results (a) Dataset A; (b) Dataset B. The adopted evaluation metrics include Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), maximum prediction error, and coefficient of determination (R2). Among them, the first three indicators are used to describe the deviation between the predicted value and the true value. The smaller their values are, the better the model’s predictive ability for extreme situations and the more stable the prediction. We use R² to measure the model’s forecasting accuracy. The closer its value is to 1, the stronger the model’s fitting ability. The specific calculation formulas for each evaluation indicator are provided below: where, n denotes the total number of samples, ({y_i}) represents the actual photovoltaic power of the i-th sample, ({hat {y}_i}) is its predicted value, and (bar {y}) represents the average power of the entire sample set. This paper comprehensively validates the predictive performance and generalization capability of the VMD-CNN-IWMA-KELM model across two power plant datasets through five analytical approaches: comparison of actual and predicted values, model evaluation metrics analysis, linear regression analysis, ablation studies, and model complexity analysis. Figure 11 presents the simulation diagrams of the predicted values and the true values of the four single-step models, BP, ELM, SVR, and KELM, as well as the CNN-KELM hybrid model on the two datasets. Through observation, we can see that the predicted curve of the single-step model deviates significantly from the actual value, especially in the rapid fluctuation range of power, where the gap is relatively large. Its adaptability to the complex fluctuation characteristics of photovoltaic power is insufficient. Compared with the KELM model, the fit between the prediction curve of the CNN-KELM hybrid model and the actual value is improved. Especially on dataset B, which exhibits greater volatility, its predicted values consistently align more closely with the actual values, demonstrating superior robustness. This indicates that the sequential local pattern capture and spatio-temporal correlation feature extraction capabilities of CNN are effectively complementary to the efficient nonlinear fitting capabilities of KELM. As a result, this makes up for the deficiencies of the KELM model in feature extraction and nonlinear adaptability, and improves the accuracy of PV power forecasting. Therefore, the necessity of using CNN-KELM as the baseline model is validated. Predictive simulation diagrams for BP, ELM, SVR, KELM, CNN-KELM. (a) Dataset A; (b) Dataset B. Figure 12 presents the simulation diagrams of the KELM, CNN-KELM, CNN-WMA-KELM and CNN-IWMA-KELM models on two datasets. We can observe that after the CNN-KELM model initially improves the performance of the KELM model, the introduction of an intelligent optimization algorithm further enhances the model’s fitting ability. With the introduction of IWMA algorithm, its predicted value curve is closer to the true value curve, and the prediction effect of the model is better. For the strong fluctuating trends in the detailed diagrams, CNN-IWMA-KELM can accurately capture them. This result demonstrates that by using the IWMA algorithm to optimize the hyperparameters in the CNN-KELM hybrid model, during the parameter optimization process, the model can accurately find the parameters that are most suitable for the model, which can effectively alleviate the limitations of parameter selection on the model performance. Accordingly, the model’s prediction accuracy is improved, while its robustness is also enhanced. Predictive simulation diagrams for KELM, CNN-KELM, CNN-WMA-KELM, CNN-IWMA-KELM. (a) Dataset A; (b) Dataset B. Figure 13 presents the prediction simulation diagrams of the KELM, CNN-KELM, and VMD-CNN-KELM models. By comparison, it can be observed that that the performance of the model on the two data sets is consistent after the inclusion of the VMD method. Its prediction performance is further improved compared with the KELM and CNN-KELM models. Especially in the multiple rapid power fluctuation intervals present in Dataset B, the VMD-CNN-KELM model can accurately capture the variations, achieving the closest overlap with the actual value curve. This indicates that VMD greatly reduces the nonlinearity and complexity of the data by disintegrating the original complex power sequence into multiple modal components of simple frequencies. At this stage, the CNN model in VMD-CNN-KELM doesn’t need to learn the complex multi-scale features of the original sequence anymore. It only needs to focus on the individual fluctuation patterns of each modal component. This not only reduces the learning difficulty but also improves the accuracy of feature extraction. Therefore, the decomposition operation enhances the learnability of features. This enables the model to effectively enhance its ability to capture fluctuation segments and its prediction accuracy. Therefore, the effectiveness of introducing the VMD module is verified. Predictive simulation diagrams for KELM, CNN-KELM, VMD-CNN-KELM. (a) Dataset A; (b) Dataset B. Figure 14 presents the prediction simulation diagrams of the nine models selected in this study on two datasets. From the R2 results, the single-step prediction model has deficiencies in prediction accuracy on the two test sets, capture of fluctuations, and trend fitting. In contrast, the multi-step prediction models demonstrate superior predictive capability. Among them, the VMD-CNN-IWMA-KELM model has a prominent performance in the prediction of photovoltaic power generation. Its prediction curve shows a superior fit to the actual value, and it captures the shape of the power peak, the amplitude of the valley and the trend of the rapid fluctuation section with the highest precision. Through the deep collaboration of multi-modules of feature extraction, hyperparameter exploration and sequence decomposition, this model markedly surpasses the others for forecasting accuracy and robustness. Therefore, it fully validates that the VMD-CNN-IWMA-KELM model possesses outstanding predictive capability in photovoltaic power forecasting applications. Predictive simulation diagrams for nine models. (a) Dataset A; (b) Dataset B. The simulation experiments present the detailed results of the nine forecasting models for root mean square error (RMSE), mean absolute error (MAE), maximum prediction error (({delta _{hbox{max} }})), and coefficient of determination (R²) in Table 8. To clearly visualize the variations in these metrics, we present histograms of the evaluation indicators for the nine models in Figs. 15 and 16. After comparing the results of the single-step models and the CNN-KELM model, we can see that all single-step models have R² values below 0.9 and 0.8, respectively, and exhibit relatively large errors. Although the KELM model outperforms the ELM model, it still exhibits poor robustness and low accuracy, failing to meet the prediction expectations. In contrast, the CNN-KELM model, which combines the advantages of CNN and KELM, can effectively enhance the model’s prediction performance. Relative to the KELM, the CNN-KELM model increases the R2 by 4.05% and 4.66% on the two power station datasets, respectively. Meanwhile, it significantly reduces the model’s error metrics. Thus, this verifies the synergistic advantages of the dual-module architecture combining CNN’s local feature extraction and KELM’s nonlinear processing. By comparing the indicators of the CNN-KELM, CNN-WMA-KELM and CNN-IWMA-KELM models, we can know that intelligent optimization algorithms can improve the prediction accuracy. Among them, the optimization effect of IWMA algorithm proposed in this paper is more obvious. Its RMSE and MAE are reduced, and compared with the CNN-KELM, the R² of the CNN-IWMA-KELM model is increased by 3.91% and 5.52%, respectively. This improvement stems from the iterative optimization mechanism of the IWMA algorithm. It can search the hyperparameters corresponding to the optimal fitness through continuous iterative update, which effectively alleviates the problem of model inefficiency caused by the randomness of hyperparameters and improves the prediction ability. By comparing the prediction results of the CNN-KELM and VMD-CNN-KELM, it can be observed that the evaluation indexes of the model are further optimized by incorporating the VMD signal decomposition method. In the two power station datasets, compared with the CNN-KELM, their RMSE is reduced by 25.85% and 25.44%, and MAE is reduced by 15.93% and 27.73%, respectively. R² values for Dataset A and Dataset B are 93.15% and 91.14%, indicating a satisfactory prediction performance. Therefore, the model can effectively reduce prediction errors caused by the nonlinear and non-stationary characteristics of the original photovoltaic power series through adaptive decomposition using VMD, thus improving its forecasting accuracy. A comprehensive comparison of nine forecasting model evaluation metrics indicates that CNN-KELM, CNN-IWMA-KELM, VMD-CNN-KELM, and VMD-CNN-IWMA-KELM all demonstrate outstanding performance in PV power forecasting. Specifically, CNN-KELM leverages the powerful feature extraction capability of CNN to fully exploit the advantages of the hybrid model. With parameter optimization by IWMA, the CNN-IWMA-KELM model achieves R² values of 91.45% and 89.57% on the two datasets, approaching the optimal performance under the given architectural constraints. By smoothing noise through modal decomposition, the VMD-CNN-KELM model further improves the R² values to 93.15% and 91.14%. By integrating the advantages of all three components, the VMD-CNN-IWMA-KELM model achieves R² values of 96.71% and 92.33%, effectively capturing power variation trends and fully demonstrating the superiority of the proposed model. Comparison of evaluation indicators for dataset A. Comparison of evaluation indicators for Dataset B. In order to quantify the linear correlation and error distribution between the predictive model outputs and the actual photovoltaic power, linear regression analysis is introduced as an evaluation method to intuitively reflect the matching degree between the forecasted and the actual outputs, with the results shown in Fig. 17. In both datasets, the VMD-CNN-IWMA-KELM model exhibits better goodness of fit, with values all above 90%, and a more concentrated error distribution. Compared with multi-step models, single models exhibit a more discrete error distribution in both data types. Furthermore, through signal decomposition and algorithm optimization, by integrating the advantages of VMD and IWMA into the CNN-KELM model, the forecasting accuracy of the model is improved to varying degrees. Therefore, the VMD-CNN-IWMA-KELM model proposed in this study demonstrates superior adaptability and robustness across different test sets, and exhibits strong predictive capability in photovoltaic power prediction scenarios. Linear regression graph of predicted and true values (a) Dataset A; (b) Dataset B. To quantify the impact of each part in the VMD-CNN-IWMA-KELM model, we design ablation experiments. We adopt CNN-KELM as the baseline model and then separately introduce the IWMA optimization algorithm and VMD decomposition model to construct four comparative models: CNN-KELM, CNN-IWMA-KELM, VMD-CNN-KELM, and VMD-CNN-IWMA-KELM. We keep the parameter settings of all models consistent with those in Table 6 and present the experimental results in Table 9. Based on the experimental results obtained from two datasets, introducing the optimization algorithm and the signal decomposition module, respectively, improves the prediction performance to varying degrees compared with the CNN-KELM baseline model. Above all, integrating the IWMA optimization algorithm into the CNN-KELM model reduces the RMSE, MAE, and ({delta _{hbox{max} }}) on both datasets. Specifically, the RMSE and MAE of dataset A are reduced by 17.19% and 6.99%, respectively. The RMSE and MAE of dataset B are reduced by 19.13% and 26.71%, respectively. In addition, the R2 increases by 3.91% and 5.52%, respectively. This indicates the necessity of using IWMA algorithm for hyperparameter optimization. Then, after incorporating the VMD signal decomposition module, the error metrics for both datasets are further reduced. It also improves the fitting ability. Finally, we integrate these two components to form the VMD-CNN-IWMA-KELM model. The proposed model has a smaller maximum error than the CNN-KELM model. On Dataset A, the error drops from 22.1424 to 8.1332. On Dataset B, it drops from 11.5586 to 6.7756. The R² values increase to 96.71% and 92.33%, respectively. The results indicate that incorporating VMD and IWMA into the CNN-KELM model can effectively enhances prediction accuracy of the model by combining the advantages of signal decomposition and parameter optimization. Therefore, the ablation experiments verify that each module of the model exhibits its own unique role. Using data from two power stations, the generalization ability and robustness of the model are verified, further demonstrating the effectiveness of the proposed VMD-CNN-IWMA-KELM model. The time consumption of the model serves as a crucial indicator for performance evaluation. This paper analyzes the time complexity of the 9 selected models, and the results are presented in Table 10. We can observe that compared with the single-step model, the VMD-CNN-IWMA-KELM prediction model proposed in this paper requires a longer running time for implementation. This is due to the introduction of the intelligent optimization algorithm, which increases the overall operating cost of the model due to factors such as population size, number of iterations, and the internal computational structure of the algorithm. Although the model takes a long time to run, in the deployment system of practical engineering applications, the model training module will be completed in advance before building the prediction system, and the prediction stage can be finished in just a few seconds. Therefore, VMD-CNN-IWMA-KELM model can achieve more accurate prediction outcomes within a reasonable time. Photovoltaic power generation power prediction is a key prerequisite for ensuring the stable operation of the power system and promoting the large-scale development of photovoltaic power. However, photovoltaic power has intermittency and non-stationarity, which seriously affects the prediction accuracy. Therefore, this paper takes short-term photovoltaic power as the research object and constructs a multi-step forecasting model based on VMD and IWMA algorithm. This model takes CNN-KELM as the basic framework. Firstly, VMD is utilized to decompose the original power signal to suppress noise interference and improve the quality of input data. Furthermore, the Improved Whale Migration Algorithm (IWMA) optimized by the Lévy flight strategy based on chaotic mapping, dynamic inertia weight, and dynamic factor adjustment is adopted to optimize the hyperparameters of the CNN-KELM hybrid model, thereby enhancing the model’s prediction accuracy. Finally, the multi-step hybrid prediction model proposed in this study is evaluated and compared through a series of experiments, which validates its effectiveness. We can draw the following conclusions: We combine the CNN model with the KELM model. This fixes the problem that the single KELM model is weak at extracting features. Leveraging their complementarity, it achieves a complete functionality from automatic feature extraction to efficient nonlinear fitting. The experimental results confirm that, compared with the KELM single-step model, the CNN-KELM hybrid model demonstrates higher prediction accuracy in the prediction. The R2 improvement on the two datasets is 4.05% and 4.66%, respectively, highlighting the advantages of the CNN-KELM hybrid structure over the single-step model. The IWMA algorithm proposed in this paper effectively boosts the optimization ability of WMA the algorithm. By applying the IWMA algorithm to the hyperparameter optimization of the CNN-KELM model, it significantly improves model prediction performance. Variational Mode Decomposition (VMD) can adaptively decompose the original PV generation power sequence into multiple single-frequency stationary mode components (IMFs). This method effectively alleviates the mode aliasing problem, reduces the prediction error caused by data noise, enhances the fitting ability of strong nonlinear and non-stationary signals, and then improves the quality of model input. On two power station datasets, comparative experiments are carried out on nine models. The results show that the proposed VMD-CNN-IWMA-KELM multi-step prediction model has a closest fit between the predicted curve and the actual values, achieving the best fitting performance. The goodness-of-fit values are 96.71% and 92.33%, respectively, and the model’s error metrics are the smallest. This fully demonstrates its notable advantages in PV power sequence decomposition and feature extraction, and can achieve more accurate PV power prediction. Overall, the VMD-CNN-IWMA-KELM multi-step forecasting model can overcome the limitations of single models, comprehensively enhance the model’s prediction performance, and demonstrate high adaptability in photovoltaic power prediction. This model can also be extended to complex prediction and classification tasks that require simultaneously handling multi-scale patterns, local features, and nonlinear relationships, such as bearing fault diagnosis, power load forecasting, arrhythmia detection, and hazard evaluation. Although this study has constructed a VMD-CNN-IWMA-KELM multi-step short-term photovoltaic power prediction model and achieved favorable results, it still has certain limitations. First, the data utilized in this experiment covers two seasons, namely winter and summer. While it encompasses most common weather conditions, the predictive performance of the model has not been validated under extreme weather scenarios such as severe sandstorms, strong winds, and heavy snowstorms. Second, during the model validation process, the number of comparative models currently selected is relatively limited, and they do not yet cover predictive architectures such as CNN-LSTM, CNN-GRU, or those based on Transformer. Given these limitations, future research will incorporate additional parameter variables and further enhance the model’s generalization capability and stability under extreme weather conditions. Meanwhile, CNN-LSTM, CNN-GRU, and Transformer-based prediction models will be incorporated for comparative analysis to fully demonstrate the superiority of the VMD-CNN-IWMA-KELM model. In addition, the IWMA algorithm will continue to be optimized to meet the demand for high-precision parameter optimization under extreme meteorological conditions, thereby further enhancing the model’s predictive performance and robustness. The datasets generated and analyzed in the present study are available from the corresponding author upon reasonable request. Alternating direction method of multipliers Autoregressive integrated moving average model Autoregressive moving average model Bidirectional long short-term memory Back propagation Butterfly optimization algorithm Convolutional neural network Dung beetle optimizer Extreme learning machine Empirical mode decomposition Fractional whale optimization algorithm Greylag goose optimization Intrinsic mode function Improved whale migration algorithm Improved dung beetle optimizer Improved moth-flame optimization Kernel extreme learning machine Least squares support vector machine Long short-term memory Multilayer perceptron Maximum power point tracking Parrot optimizer Photovoltaic Power law model Single-diode model Support vector machine Support vector regression Time – variable filtering Variational mode decomposition Whale migration algorithm Wavelet transform Whale optimization algorithm Nie, X. P. et al. Emerging renewable-based electricity grids under high penetration of cleaner prosumers: Unraveling the flexibility issues using a four-layer decentralized mechanism. J. Clean. Prod.443, 141107 (2024). Article Google Scholar Keddouda, A. et al. Solar photovoltaic power prediction using artificial neural network and multiple regression considering ambient and operating conditions. Energy Convers. Manag.288, 117186 (2023). Article Google Scholar Navesi, R. B. et al. Reliable operation of reconfigurable smart distribution network with real-time pricing-based demand response. Electr. Power Syst. Res.241, 111341 (2025). Article Google Scholar Emdadi, K. & Pirouzi, S. Benders decomposition-based power network expansion planning according to eco-sizing of high-voltage direct-current system, power transmission cables and renewable/non-renewable generation units. IET Renew. Power Gener. 19, e70025 (2025). Article Google Scholar Gupta, R. et al. Composition of feature selection techniques for improving the global horizontal irradiance estimation via machine learning models. Therm. Sci. Eng. Prog.48, 102394 (2024). Article Google Scholar Yao, M. et al. Stochastic economic operation of coupling unit of flexi-renewable virtual power plant and electric spring in the smart distribution network. IEEE Access11, 75979–75992 (2023). Article Google Scholar Mansouri, S. A. et al. An IoT-enabled hierarchical decentralized framework for multi-energy microgrids market management in the presence of smart prosumers using a deep learning-based forecaster. Appl. Energy. 333, 120560 (2023). Article Google Scholar Ra, N., Varman, S. & Bhattacharjee, A. Prediction of optical performance of solar PV under the impact of natural dust accumulation: machine learning approach. In 2023 IEEE IAS Global Conference on Renewable Energy and Hydrogen Technologies (GlobConHT) 1–5 (2023). Xu, M. & Zhang, C. Time-segment photovoltaic prediction method based on multi-objective slime mold algorithm to improve support vector machine. In 2023 International Conference on Power Energy Systems and Applications (ICoPESA) 648–654 (2023). Sharkawy, A. N. et al. Solar PV power estimation and upscaling forecast using different artificial neural networks types: assessment, validation, and comparison. IEEE Access11, 19279–19300 (2023). Article Google Scholar Shi, J. et al. Four-stage space-time hybrid model for distributed photovoltaic power forecast-ting. IEEE Trans. Ind. Appl.59, 1129–1138 (2022). Article Google Scholar Javadi, M. et al. Very short-term PV power prediction using machine learning models. In IEEE Canadian Conference on Electrical and Computer Engineering (CCECE). 55–59 (2022). Gupta, R., Yadav, A. K., Jha, S. & Pathak, P. K. A robust regressor model for estimating solar radiation using an ensemble stacking approach based on machine learning. Int. J. Green Energy21(8), 1853–1873 (2024). Article Google Scholar Gupta, R. et al. Predicting global horizontal irradiance of north central region of India via machine learning regressor algorithms. Eng. Appl. Artif. Intell.133, 108426 (2024). Article Google Scholar Zhi, Y., Sun, T. & Yang, X. A physical model with meteorological forecasting for hourly rooftop photovoltaic power prediction. J. Build. Eng.75, 106997 (2023). Article Google Scholar Zaimi, M., El Ainaoui, K. & Assaid, E. M. Mathematical models to forecast temporal variations of power law shape parameters of a PV module working in real weather conditions: Prediction of maximum power and comparison with single-diode model. Solar Energy266, 112197 (2023). Article Google Scholar Mayer, M. J. & Gróf, G. Extensive comparison of physical models for photovoltaic power forecasting. Appl. Energy283, 116239 (2021). Article Google Scholar Nachtigall, R. et al. Revealing the effects of data heterogeneity in federated learning regression models for short-term solar power forecasting. IEEE Access12, 171472–171487 (2024). Sapundzhi, F. et al. Predictive modeling of photovoltaic energy yield using an ARIMA approach. Appl. Sci.14, 11192 (2024). ArticleCAS Google Scholar Jung, A. H. et al. Regional photovoltaic power forecasting using vector autoregression model in South Korea. Energies15, 7853 (2022). Article Google Scholar Fara, L. et al. Forecasting of energy production for photovoltaic systems based on ARIMA and ANN advanced models. Int. J. Photoenergy2021, 6777488 (2021). Souhe, F. G. Y. et al. Optimized forecasting of photovoltaic power generation using hybrid deep learning model based on GRU and SVM. Electr. Eng.106, 7879–7898 (2024). Article Google Scholar Ge, J. et al. Short-term prediction of PV output based on weather classification and SSA-ELM. Front. Energy Res.11, 1145448 (2023). Article Google Scholar Gupta, R., Yadav, A. K., Jha, S. & Pathak, P. K. Time series forecasting of solar power generation using facebook prophet and xg boost. In 2022 IEEE Delhi Section Conference (DELCON) 1–5 (2022). Zang, H. et al. Day-ahead photovoltaic power forecasting approach based on deep convolutional neural networks and meta learning. Int. J. Electr. Power Energy Syst.118, 105790 (2020). ArticleADS Google Scholar Hu, Z. et al. Improved multistep ahead photovoltaic power prediction model based on LSTM and self-attention with weather forecast data. Appl. Energy359, 122709 (2024). Article Google Scholar Li, M. et al. Deep learning model for short-term photovoltaic power forecasting based on variational mode decomposition and similar day clustering. Comput. Electr. Eng.155, 109116 (2024). ArticleADS Google Scholar Lu, F. et al. A comparative study of photovoltaic power prediction models based on BP and SVR. In Proc. 6th Int. Conf. Robot. Intell. Control Artif. Intell. (RICAI), IEEE. 771–744 (2024). Wadood, A. et al. Design of a novel fractional whale optimization-enhanced support vector regression (FWOA-SVR) model for accurate solar energy forecasting. Fractal Fract.9, 55 (2025). Article Google Scholar Zhao, M. & Zhou, X. Multi-step short-term wind power prediction model based on CEEMD and improved snake optimization algorithm. IEEE Access12, 50755–50778 (2024). Article Google Scholar Shi, S. et al. Short time solar power forecasting using P-ELM approach. Sci. Rep.14, 30999 (2024). ArticleADSCASPubMedPubMed Central Google Scholar Li, N. et al. Research on short-term photovoltaic power prediction based on multi-scale similar days and ESN-KELM dual core prediction model. Energy277, 127557 (2023). Article Google Scholar Singh, P., Singh, N. K. & Singh, A. K. Wavelet transform based gated-recurrent unit deep learning approach for power output of solar photovoltaic system forecasting. SN Comput. Sci.6, 243 (2025). Article Google Scholar Khelifi, R. et al. Short-term PV power forecasting using a hybrid TVF-EMD-ELM strategy. Int. Trans. Electr. Energy Syst.2023, 6413716 (2023). Liu, L., Zhang, J. & Xue, S. Photovoltaic power forecasting: Using wavelet threshold denoising combined with VMD. Renew. Energy249, 123152 (2025). Article Google Scholar Xiong, S. et al. Power data prediction method of new energy system based on wavelet transform and adaptive hybrid optimization. Int. J. Low-Carbon Technol.19, 723–732 (2024). Article Google Scholar Zhao, Y. et al. Photovoltaic power generation power prediction under major extreme weather based on VMD-KELM. Energy Eng.121, 3711 (2024). Article Google Scholar Bashir, T. et al. Wind and solar power forecasting based on hybrid CNN-ABiLSTM, CNN-transformer-MLP models. Renew. Energy239, 122055 (2025). Article Google Scholar Jiang, J. et al. Short-term PV power prediction based on VMD-CNN-IPSO-LSSVM hybrid model. Int. J. Low-Carbon Technol.19, 1160–1167 (2024). Article Google Scholar Meng, J. et al. Short-term prediction of rural photovoltaic power generation based on improved dung beetle optimization algorithm. Sustainability16, 5467 (2024). ArticleADSCAS Google Scholar Guo, Z. et al. Short term photovoltaic power prediction based on VMD-IMFO-KELM. In 2025 4th International Conference on Power System and Energy Techno-logy (ICPSET) 333–338 (2025). Ghasemi, M. et al. An efficient bio-inspired algorithm based on humpback whale migration for constrained engineering optimization. Results Eng.25, 104215 (2025). Article Google Scholar Dragomiretskiy, K. & Zosso, D. Variational mode decomposition. IEEE Trans. Signal Process.62, 531–544 (2013). ArticleADSMathSciNet Google Scholar Li, Z. et al. A survey of convolutional neural networks: analysis, applications, and prospects. IEEE Trans. Neural Netw. Learn. Syst.33, 6999–7019 (2021). ArticleADSMathSciNet Google Scholar Kiranyaz, S. et al. 1D convolutional neural networks and applications: A survey. Mech. Syst. Signal Process.151, 107398 (2021). Article Google Scholar Huang, G. B., Zhu, Q. Y. & Siew, C. K. Extreme learning machine: a new learning scheme of feedforward neural networks. In Proc. IEEE Int. Joint Conf. Neural Netw.2, 985–990 (2004). Fister, I. Jr. et al. A review of chaos-based firefly algorithms: Perspectives and research challenges. Appl. Math. Comput.252, 155–165 (2015). Zhang, C. & Ding, S. A stochastic configuration network based on chaotic sparrow search algorithm. Knowl.-Based Syst.220, 106924 (2021). Article Google Scholar Shi, Y. & Eberhart, R. A modified particle swarm optimizer. In Evolutionary Computation Proceedings, 890, 69–73 (1998). Wang, J. et al. A hybrid particle swarm optimization algorithm with dynamic adjustment of inertia weight based on a new feature selection method to optimize SVM parameters. Entropy25, 531 (2023). ArticleADSPubMedPubMed Central Google Scholar Reynolds, A. M. & Rhodes, C. J. The Lévy flight paradigm: Random search patterns and mechanisms. Ecology90, 877–887 (2009). ArticleCASPubMed Google Scholar Arora, S. & Singh, S. Butterfly optimization algorithm: A novel approach for global optimization. Soft Comput.23, 715–734 (2019). Article Google Scholar Mirjalili, S. & Lewis, A. The whale optimization algorithm. Adv. Eng. Softw.95, 51–67 (2016). Article Google Scholar El-Kenawy, E. S. M. et al. Greylag goose optimization: Nature-inspired optimization algori-thm. Expert Syst. Appl.238, 122147 (2024). Article Google Scholar Xue, J. & Shen, B. Dung beetle optimizer: A new meta-heuristic algorithm for global optimization. J. Supercomput79, 7305–7336 (2023). Article Google Scholar Lian, J. et al. Parrot optimizer: Algorithm and applications to medical problems. Comput. Biol. Med.172, 108064 (2024). ArticlePubMed Google Scholar Zhou, M. et al. An industrial load classification method based on a two-stage feature selection strategy and an improved MPA-KELM classifier: A Chinese cement plant case. Electronics12, 3356 (2023). Article Google Scholar Download references College of Science, Xi’an University of Science and Technology, Xi’an, 710054, China Mengling Zhao, Shan Wu & Yibo Hu Search author on:PubMedGoogle Scholar Search author on:PubMedGoogle Scholar Search author on:PubMedGoogle Scholar S.W. writes the body of the manuscript, and M.Z. and Y.H. check the paper. All authors review the manuscript. Correspondence to Shan Wu. The authors declare no competing interests. Funding is provided by National Natural Science Foundation of China (Grant no: 12401265). Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/. Reprints and permissions Zhao, M., Wu, S. & Hu, Y. A multi-step short-term photovoltaic power prediction model based on an improved whale migration algorithm. Sci Rep16, 10537 (2026). https://doi.org/10.1038/s41598-026-41673-2 Download citation Received: Accepted: Published: Version of record: DOI: https://doi.org/10.1038/s41598-026-41673-2 Anyone you share the following link with will be able to read this content: Sorry, a shareable link is not currently available for this article.
You must be logged in to post a comment.