MUMBAI, India, May 29 -- Intellectual Property India has published a patent application (202641061667 A) filed by Sr University, Warangal, Telangana, on May 14, for 'federated deep learning framework for privacy-preserving solar radiation forecasting.'
Inventor(s) include Bongoni Naresh; and Dr. Amit Kumar Yadav.
The application for the patent was published on May 29, under issue no. 22/2026.
According to the abstract released by the Intellectual Property India: "A federated deep learning framework for privacy-preserving solar radiation forecasting across distributed energy systems is disclosed. The framework enables geographically distributed energy nodes including solar farms, rooftop photovoltaic systems, smart buildings, and microgrids to collaboratively train deep learning forecasting models without sharing raw local datasets. Each node independently performs local model training using locally available environmental and solar irradiance data. Encrypted model updates are transmitted to a federated aggregation server configured to generate a global forecasting model through federated aggregation techniques. Privacy preservation is achieved using encryption protocols, secure aggregation mechanisms, and differential privacy techniques. Communication overhead is reduced through parameter compression, quantization, and gradient sparsification methods. The framework improves forecasting accuracy, scalability, communication efficiency, and privacy protection in distributed renewable energy forecasting environments. The invention is suitable for smart grids, renewable energy optimization systems, intelligent energy management platforms, and distributed energy infrastructures."
Disclaimer: Curated by HT Syndication.
