Research on Energy Management Strategy of Electric Vehicle Hybrid System Based on Reinforcement Learning

Abstract

From the perspective of energy management, the demand power of a hybrid electric vehicle driving under random conditions can be considered as a random process, and the Markov chain can be used for modeling. In this article, an energy management strategy based on reinforcement learning with real-time updates is proposed to reasonably allocate the energy flow of the hybrid power system under unknown working conditions. The hybrid system is powered by a supercapacitor and a lithium battery, which uses the characteristics of each component to reduce the energy loss of the system, reduce the rate of change of the lithium battery current, and prolong the service life of the components. The strategy takes the change of the transition probability matrix under real-time working conditions as the basis. The system judges whether it is necessary to use the new transition probability to calculate and update the energy management strategy of the system by calculating the Pearson similarity between the transition probability matrix at the current time and previous time. The simulation results validate the proposed method.