Unlocking Ultrafast Charging: Reinforcement Learning With Reliability Guarantee for Ultrafast EV Charging Hub Under Behavior Uncertainty

The direct current (DC) ultrafast electric vehicle charging hub (UFEVCH) represents a cutting-edge infrastructure designed to meet the growing high-power charging demands of electric vehicles (EVs) and support the goal of carbon neutrality. The way that UFEVCH realizes ultrafast charging is its ability to gather power by allocating power modules (PMs) to charging dispensers. Intelligent and real-time dispatching of PMs can enhance the overall utilization rate of UFEVCH and reduce losses associated with frequent reallocation. However, the PM dispatch has yet to be comprehensively studied. This study introduces a novel UFEVCH model that simulates the operational conditions of PMs and formulates a PM dispatch problem to achieve a higher utilization rate and modular cost-effectiveness. A real-time PM dispatch method, termed reinforcement learning and secondary dispatch (RLSD), is proposed to accommodate the uncertain behavior of EV charging. This method employs reinforcement learning (RL) to optimize PM allocation in real-time. In addition, the secondary dispatch (SD) ensures the reliability of UFEVCH by refining the RL solutions. The proposed UFEVCH model and RLSD method are validated using data from over 100 practical UFEVCH in Shenzhen, China, demonstrating nearly doubled service quality compared with numerous model-free and model-based methods. In addition, a theoretical analysis is provided to illustrate the convergence of the RLSD method.