A Deep Reinforcement Learning Method for Unit Commitment with Renewable Energy Generators

Abstract

To cope with the challenges of complex modeling, difficult solutions, and low efficiency brought by a significant amount of renewable energy units to the power system dispatch (PSD), a deep reinforcement learning method for unit commitment with renewable energy generators is proposed. Firstly, a PPO-based reinforcement learning method is utilized to promptly and effectively resolve the unit commitment. A mathematical optimization technique is employed to solve the security-constrained economic dispatch, considering the “N-1” security check. By integrating these two methods, the decision-making efficiency is enhanced while ensuring the security of the result. The proposed method’s efficiency is affirmed by case simulation.