A Coordinated Charging Strategy for Electric Vehicles Based on a Reinforcement Learning Algorithm

The large-scale adoption of electric vehicles presents certain challenges to the safe and stable operation of the distribution network. In response to the interaction issue between large-scale electric vehicles and the distribution network, an interaction method is proposed based on deep reinforcement learning for electric vehicles and the distribution network. First, a coupled model integrating electric vehicles, the traffic network, and the distribution network is constructed, and mathematical models for electric vehicles, photovoltaics, and energy storage are respectively formulated. Subsequently, considering the interaction among photovoltaics, energy storage, and the distribution network, a coordinated charging strategy for electric vehicles is developed based on the improved deep deterministic policy gradient algorithm. This strategy aims to meet user charging demands, minimize the operating costs of charging stations, and promote new energy consumption. Finally, taking the electric vehicles and distribution network of a specific city as a case study, the effectiveness and superiority of the interaction strategy based on this algorithm are verified.