MUMBAI, India, May 29 -- Intellectual Property India has published a patent application (202531133328 A) filed by National Institute Of Technology, Rourkela, Orissa, on Dec. 30, 2025, for 'machine-learning-based adaptive control system and method for community-level battery storage demand side management.'
Inventor(s) include Ray, Dr. Pravat Kumar; Nandkeolyar, Dr. Shobhit; Puhan, Dr. Pratap Sekhar; and Panda, Dr. Gayadhar.
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: "The present invention relates to a demand side management system (500) and a method (600) for a community-level power distribution network. The system (500) comprises a battery storage system (BSS) coupled to a distribution grid at a point of common coupling (PCC) through a bidirectional power conversion unit, one or more sensing units for acquiring real-time operational parameters, and a control unit coupled to the sensing units and the bidirectional power conversion unit. The control unit implements a machine-learning-based control architecture comprising a convolutional neural network (CNN), a long short-term memory network (LSTM), and a deep neural network (DNN). The control architecture processes operational parameters to determine the operating state of the battery storage system and a corresponding power reference value and generates pulse width modulation (PWM) control signals. The method (600) enables charging and discharging to reduce peak demand. The present invention is applicable in community-level power distribution networks."
Disclaimer: Curated by HT Syndication.
