MUMBAI, India, April 17 -- Intellectual Property India has published a patent application (202521085894 A) filed by Pandit Deendayal Energy University, Gandhinagar, Gujarat, on Sept. 10, 2025, for 'edge-based transformer monitoring and load optimization for smart power grids.'
Inventor(s) include Aneri Shah; Krish Modi; Ansh Soni; and Dr. Nishant Doshi.
The application for the patent was published on April 17, under issue no. 16/2026.
According to the abstract released by the Intellectual Property India: "The invention provides a decentralized system for transformer health monitoring and load optimization within power grids. It utilizes an edge device installed at each transformer site to perform on-device prediction, fault detection, and load balancing without relying on continuous internet connectivity. The system includes a Long Short-Term Memory (LSTM) model for predicting Remaining Useful Life (RUL), an autoencoder model for real-time anomaly detection, and a Multi-Agent Deep Q-Network (DQN) for local load control. All models operate independently on the edge, ensuring fast, privacy-preserving, and resilient transformer management. The system further supports Over-The-Air (OTA) updates, enabling remote model improvements without physical intervention. A user dashboard provides health scores, failure probabilities, and actionable maintenance insights. This invention improves grid reliability, reduces power losses, and enhances transformer lifespan- making it ideal for smart grids, especially in low-connectivity or distributed environments."
Disclaimer: Curated by HT Syndication.
