Intellectual Property India Publishes Patent Application for 'AI-Driven Energy Storage Optimization System For Microgrid Applications' Filed by Dr. M. Antony Freeda Rani; Mr. Binu Packia Ananth; Mrs. P. S. Meenambikai; Mrs. N. Anita Femilin; Mrs. J. Jenibha Joshi; Dr. G. Murugan; Mrs. Kavitha R N; Mrs. R. Brindha Shalini; Mrs. S. Nithya; and Mrs. I. Anita Merlin

MUMBAI, India, March 13 -- Intellectual Property India has published a patent application (202641024393 A) filed by Dr. M. Antony Freeda Rani; Mr. Binu Packia Ananth; Mrs. P. S. Meenambikai; Mrs. N. Anita Femilin; Mrs. J. Jenibha Joshi; Dr. G. Murugan; Mrs. Kavitha R N; Mrs. R. Brindha Shalini; Mrs. S. Nithya; and Mrs. I. Anita Merlin, Kanyakumari, Tamil Nadu, on March 1, for 'ai-driven energy storage optimization system for microgrid applications.'

Inventor(s) include Dr. M. Antony Freeda Rani; Mr. Binu Packia Ananth; Mrs. P. S. Meenambikai; Mrs. N. Anita Femilin; Mrs. J. Jenibha Joshi; Dr. G. Murugan; Mrs. Kavitha R N; Mrs. R. Brindha Shalini; Mrs. S. Nithya; and Mrs. I. Anita Merlin.

The application for the patent was published on March 13, under issue no. 11/2026.

According to the abstract released by the Intellectual Property India: "The trend of using renewable sources of energy in microgrids requires smart and dynamic energy storage management systems. The paper is the work on an AI-based energy storage optimization system to enhance the microgrid performance and operational efficiency, reliability, and economic performance. The suggested structure incorporates machine learning, deep reinforcement learning, and predictive analytics in order to allow to optimize battery charging and discharging cycles in real-time. Sensors and edge computing that are IoT-enabled are used to monitor continuously the parameters of load demand, renewable generation, and battery health. The state-of-charge (SoC) and state-of-health (SoH) estimation models are advanced to maximize battery performance and minimize the cost of degradation. A hybrid optimization model that takes into consideration deep neural networks and model predictive control forecasting demand and renewable variability is used. The system facilitates smooth incorporation of solar PV energy, wind power and charging infrastructure of electric vehicles. The outcomes of the simulation prove the efficiency of the energy resources and the expenses of the peak demand are lower, which is better than the standard rule-based methods, enhanced grid stability, and decreased carbon emissions. The suggested AI-based system will be a scalable and sustainable next-generation smart microgrids solution."

Disclaimer: Curated by HT Syndication.