Load Balancing and Frequency Control in 100 % Renewable Energy-Integrated Grids using Deep Reinforcement Learning

Increasing integration of renewable energy (RE) sources in power system presents significant challenges in maintaining frequency stability due to intermittent and variable nature of those sources. This paper proposes a deep deterministic policy gradient (DDPG) based approach for load frequency control in 100 % RE-integrated power system. The proposed method dynamically adjusts DC output voltage of PV to regulate system frequency and mitigate frequency deviations effectively. Unlike traditional proportional and integral (PI) controllers, the proposed approach does not rely on precise mathematical models of the system, making it more adaptable to varying operating conditions. The control model is trained to minimize frequency deviations by optimizing control actions based on system state information and frequency errors. Simulation studies on modified IEEE 39-bus power system demonstrate the effectiveness of the proposed method under variable irradiance, wind speed and load.