Reinforcement Learning for Optimal Renewable Energy Sources Scheduling

The increasing penetration of renewable energy sources (RES), such as wind and PV, in distribution systems, introduces challenges, such as optimal scheduling, due to their intermittent nature. This paper presents a reinforcement learning (RL) algorithm to address the optimal scheduling of RES in distribution systems. The primary objective is to improve the system’s technical parameters such as voltage profile and power loss. Additionally, the environmental performance index (CO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf> emission) has been assessed for the case. The presented approach is carried out with the IEEE 33-bus radial distribution network. Simulation results demonstrated that the proposed RL-based approach effectively balanced these objectives. Importantly, it also exhibited adaptability to sudden changes in system conditions, resulting decrease in the system losses.