TNN | Posted July 24, 2026 02:34 PM
Innovators from National Institute of Technology (NIT) Rourkela have developed an Artificial Intelligence (AI)-powered autonomous system for monitoring and cleaning solar plants. The innovation addresses the challenge of maintaining clean solar plants to ensure peak power generation without regular human intervention.
The system has been developed by Prof Arun Kumar, assistant professor, in collaboration with Prof Bibhudatta Sahoo, professor, and research graduates Lopamudra Hota and Biraja Prasad Nayak, from the Department of Computer Science and Engineering, NIT Rourkela. The team has secured an Indian patent titled, ‘Federated Learning based Autonomous System and Method for Monitoring and Cleaning Solar Plant’.
As solar energy capacity in India is expanding rapidly, large-scale solar farms, particularly in arid and dusty regions, face energy losses of up to 40% caused by dust, bird droppings, industrial pollutants, and other debris accumulated on solar panels. Conventional methods/practices used to clean solar panels are labour-intensive and require a large amount of water. Such practices usually rely on scheduled maintenance of the panels rather than on panel conditions.
To address these limitations, the NIT Rourkela research team has developed an autonomous mechanism powered by Federated Learning (FL), the invention provides an AI-driven framework leverages FL to enable intelligent, privacy-preserving monitoring, fault detection, and optimised cleaning recommendations for solar panels. The technology has been validated through simulation and is currently at Technology Readiness Level (TRL)-3, demonstrating proof-of-concept under controlled experimental conditions.
A key feature of the developed innovation is its privacy-preserving federated learning architecture. Contrary to conventional AI-operated systems, which share raw operational data with a centralised server, the developed technology shares encrypted data, thus addressing concerns related to privacy, bandwidth, cybersecurity, and scalability.
Prof Kumar said, “The patented system combines federated learning, edge computing, artificial intelligence, autonomous cleaning, and predictive maintenance into a single integrated sand-box platform. Notable features, including real-time edge intelligence, autonomous fault detection, selective need-based cleaning, reduced water consumption, and lower maintenance costs, make it a one-of-its-kind system.”
The developed technology can be applied directly to utility-scale solar power plants, floating solar farms, rooftop photovoltaic installations, industrial solar parks, smart city energy infrastructure, defence installations, and remote off-grid renewable energy systems.
Prof Sahoo said, “While current market solutions suffer from high capital costs and limited intelligence, our developed system integrates advanced AI capabilities for autonomous operation. Once scaled for field implementation, the technology is expected to deliver superior performance and features at approximately 10% of the cost of existing systems.”
As next step, the research team plans to test the invention for the development of a hardware prototype integrated with an IoT sensing infrastructure, and advance from simulation-based proof-of-concept to prototype validation through pilot deployments. 
Also, they target to collaborate with government agencies and industry partners to undertake field deployments and technology transfer of the developed technology. The team also plans to integrate drone-assisted inspection, multi-agent collaborative cleaning, and predictive energy yield forecasting in the next stage of this innovation.
The latest news, articles, and resources, sent to your inbox weekly.
© Copyright 2026 Bennett Coleman & Co. Ltd. All rights reserved.
Powered By 8 SAS ONE | V4.25.23

source