Cost-Effective Energy Management for EV Charging Stations based on GRU-MPC Model

With the rapid expansion of the electric vehicle (EV) industry, charging stations are increasingly challenged by economic dispatch problems driven by dynamic electricity prices, fluctuating loads, and uncertainties in renewable energy supply. This paper proposes a cost optimization control strategy for EV charging stations based on load prediction and Model Predictive Control (MPC). The proposed method employs a Gated Recurrent Unit (GRU) model for dynamic load forecasting and the GRU prediction results are integrated into the GRU-MPC framework to dynamically optimize the charging and discharging strategy of the energy storage system, thereby reducing operational costs. Simulation results demonstrate that the proposed GRU-MPC strategy minimizes weekly operating costs to 167,440 CNY with a 22-hour optimization window, achieving weekly savings of approximately 3,300 CNY compared to fuzzy control methods. The GRU-MPC cooperative optimization strategy further enhances the efficiency of the energy storage system and effectively responds to load fluctuations and electricity price changes.