Adaptive Energy Management Strategy for Hybrid Electric Vehicles Based on Reinforcement Learning

This paper proposes a real-time reinforcement learning based energy management strategy for hybrid electric vehicles. In order to improve the real-time performance and achieve learning online, the simulated experience from environment model is adopted for the learning process. To establish an accurate environment model, Markov Chain is introduced and an online recursive form of the transition probability matrix is derived, through which the statistical characteristics from the practical driving conditions can be collected. A Q-learning based strategy is built and trained online with the change of the probability matrix. Simulation results demonstrate that, the proposed strategy can effectively reduce the fuel consumption and the deviation of the state of charge of the battery from the desired point.