Recent Progress in Learning Algorithms Applied in Energy Management of Hybrid Vehicles: A Comprehensive Review

Abstract

Hybrid vehicles (HVs) that equip at least two different energy sources have been proven to be one of effective and promising solutions to mitigate the issues of energy crisis and environmental pollution. For HVs, one of the core supervisory control problems is the power distribution among multiple power sources, and for this problem, energy management strategies (EMSs) have been studied to save energy and extend the service life of HVs. In recent years, with the rapid development of artificial intelligence and computer technologies, learning algorithms have been gradually applied to the EMS field and shortly become a novel research hotspot. Although there are some brief reviews on the learning-based (LB) EMSs for HVs in recent years, a state-of-the-art and thorough review related to the applications of learning algorithms in HV EMSs still lacks. In this paper, learning algorithms applied in HV EMSs are categorized and reviewed in terms of the reinforcement learning algorithms and deep reinforcement learning algorithms. Apart from presenting the recent progress of learning algorithms applied in HV EMSs, advantages and disadvantages of different learning algorithms and LB EMSs are also discussed. Finally, a brief outlook related to the further applications of learning algorithms in HV EMSs, such as the integration towards autonomous driving and intelligent transportation system, is presented.