Raurkela: Researchers at National Institute of Technology (NIT) Raurkela have developed an artificial intelligence (AI)-enabled autonomous system that monitors and cleans solar panels only when required, a move expected to improve power generation while reducing maintenance costs and water consumption.
The technology, developed by Assistant Professor Arun Kumar, Professor Bibhudatta Sahoo and research graduates Lopamudra Hota and Biraja Prasad Nayak of the Department of Computer Science and Engineering, has been granted an Indian patent titled Federated Learning-based Autonomous System and Method for Monitoring and Cleaning Solar Plant.
India’s rapidly expanding solar sector often faces efficiency losses of around 40 per cent because of dust, bird droppings, industrial pollutants and other debris accumulating on solar panels.
Conventional cleaning methods are labour-intensive, consume large quantities of water and are generally carried out on fixed schedules rather than based on the condition of individual panels.
The NIT-R system uses federated learning, edge computing and AI to detect faults, assess panel conditions and recommend selective cleaning without transferring raw operational data to a central server.
Instead, it shares encrypted information, improving privacy, cybersecurity and scalability.
The technology has been validated through simulations and is currently at Technology Readiness Level 3.
Kumar said the integrated platform enables real-time monitoring, autonomous fault detection, predictive maintenance and need-based cleaning, reducing water use and maintenance costs.