Prediction-Based EV-PV Coordination Strategy for Charging Stations Using Reinforcement Learning

Coordinated charging activities of electric vehicles (EVs) in charging stations with distributed photovoltaic (PV) resources plays an important role in promoting PV consumption, saving electricity costs and improving profits for charging stations. However, the uncertainties caused by PV power output and EV arrivals impose grand challenges to achieve the desired optimal control performance. This paper presents a novel real-time EV-PV coordination strategy using distributed reinforcement learning (RL) agents, for providing real-time controls based on high-precision short-term prediction of PV outputs and EV arrivals, which can effectively avoid large deviations between actual and optimal conditions. The proposed RL-based control strategy can balance short-term and long-term benefits and achieve global optimization for charging stations. The feasibility and effectiveness of the proposed algorithm are verified by comprehensive case studies with realistic EV charging station data.