A Learning Energy Management System for Fuel Cell Electric Buses Considering Passenger Flow Prediction and Speed Planning

The energy management system (EMS) of fuel cell electric buses (FCEBs) significantly affects their operational costs, and its performance is closely related to driving speed. Passenger numbers impact the stop time between stations, providing foresight for speed planning. Additionally, maintaining a stable driving speed helps reduce overall energy consumption and power fluctuations, thus extending the lifespan of the fuel cell. Therefore, this paper proposes a learning-based EMS for FCEBs, which integrates speed planning that accounts for passenger flow prediction and speed stability, improving overall vehicle performance through optimized weight coefficients. The study consists of three main parts: 1) predicting passenger flow based on weather, temperature, time, and holidays, and estimating stop times; 2) planning speed with a focus on punctuality and passenger comfort, while minimizing red light waiting time to reduce frequent stop-start cycles; 3) performing multi-objective optimization weight learning, considering passenger flow prediction and speed planning. The planned speed curve is categorized into three driving modes: acceleration, steady-state, and deceleration. The weight coefficients are learned based on the power requirements in these modes, improving the overall system performance. Finally, simulations validate the effectiveness and advantages of the proposed algorithm in passenger flow prediction, punctuality, and EMS performance optimization. This approach significantly enhances passenger trust in public transportation while reducing bus operation costs.