MUMBAI, India, July 7 -- Intellectual Property India has published a patent application (202641074048 A) filed by Dr. S Parameswari; Mahendiran C R; T. Nandhini Priya; Dr. Manam Ravindra; Dr. Amaleswari Rajulapati; K. Sathiyavani; and Dr. N. P. Gopinath on June 15, 2026, for Reinforcement Learning Based Smart Scheduling Of Electric Vehicles For Peak Load Reduction In Power Distribution Networks.
Inventors include Dr. S Parameswari; Mahendiran C R; T. Nandhini Priya; Dr. Manam Ravindra; Dr. Amaleswari Rajulapati; K. Sathiyavani; and Dr. N. P. Gopinath.
The application for the patent was published on July 03, 2026, under issue no. 27/2026.
Abstract: Abstract The rapid progress of Electric Vehicle (EV) embracing has familiarized new trials to electrical distribution systems due to increased charging demand. Ungainly charging through peak ingesting periods may source transformer stress, voltage instability, condensed power quality, and higher energy charges. To overawed these matters, this discovery offerings a Reinforcement Learning (RL)-based adaptive scheduling method for effectual running of EV charging actions. The proposed system put on reinforcement education processes to perceptively regulate indicting timetables by uninterruptedly studying real-time situations within the supply network. Limitations including battery State of Charge (SOC), indicting duration, user necessities, electricity pricing, and current grid request are measured to improve indicting choices. The reinforcement learning manager absorbs through contact with the situation and progressively advances development recital using reward-driven optimization. This permits the organization to shift indicting heaps away from peak demand periods while guaranteeing opportune incriminating close and maintaining user expediency. The agenda contains smart charging places, communique interfaces, data acquisition units, monitoring organizations, and an intelligent control component. Unlike conventional approaches that trust on fixed instructions or stationary optimization, the planned key uninterruptedly acclimatizes to varying functioning settings and changing indicting designs. The application of this development instrument augments grid efficiency, lessens highest demand pressure, advances power supply reliability, and chains supportable EV integration into upcoming energy organizations. The proposed discovery offers an bright and ascendable answer for forward-looking energy management. Keywords: Reinforcement Learning, Electric Vehicle Charging, Smart Scheduling, Peak Demand Management, Distribution Network, Energy Optimization.
Disclaimer: Curated by HT Syndication.
