Published Paper Details:

The increasing integration of renewable energy sources and electric vehicles (EVs) has introduced new challenges in maintaining the stability and reliability of modern microgrids. Conventional control methods often struggle to manage the dynamic and uncertain nature of power generation and demand. Vehicle-to-Grid (V2G) technology enables electric vehicles to act as distributed energy storage systems by supplying power back to the grid whenever required. This paper presents a Rein-forcement Learning (RL)-Based Vehicle-to-Grid control system for microgrid stability using a tabular Q-learning agent. The proposed system uses a reinforcement learning algorithm to determine the optimal charging and discharging schedules of EV batteries based on real-time microgrid conditions. The RL agent continuously learns from the operating environment and makes intelligent decisions to minimize frequency deviations, reduce voltage fluctuations, improve power balance, and enhance overall system reliability. The proposed model includes renewable energy sources such as solar photovoltaic (PV), battery energy storage systems (BESS), electric vehicles, and utility grid support. The system is developed and analyzed using MATLAB/Simulink to evaluate its performance under different operating conditions. Simulation results demonstrate improved microgrid stability, ef-ficient energy management, reduced dependence on conventional generators, and enhanced utilization of renewable energy sources.