Abstract
This paper proposes an energy management strategy for a power-split plug-in hybrid electric vehicle (PHEV) based on reinforcement learning (RL). Firstly, a control-oriented power-split PHEV model is built, and then the RL method is employed based on the Markov Decision Process (MDP) to find the optimal solution according to the built model. During the strategy search, several different standard driving schedules are chosen, and the transfer probability of the power demand is derived based on the Markov chain. Accordingly, the optimal control strategy is found by the Q-learning (QL) algorithm, which can decide suitable energy allocation between the gasoline engine and the battery pack. Simulation results indicate that the RL-based control strategy could not only lessen fuel consumption under different driving cycles, but also limit the maximum discharge power of battery, compared with the charging depletion/charging sustaining (CD/CS) method and the equivalent consumption minimization strategy (ECMS).
Highlights
In recent years, as the greenhouse effect and air pollution have become increasingly severe, green energy attracts more attention in all walks of life
new energy vehicles (NEVs) can be mainly classified into three types, i.e., fuel cell vehicles, battery electric vehicles (BEVs) and hybrid electric vehicles (HEVs), and they are usually equipped with an energy storage system, such as a battery pack or a super-capacitor [1,2]
In [23], the investigators find that the reinforcement learning (RL) based Energy management strategy (EMS) cannot only guarantee the vehicle dynamic performance, and improve the fuel economy, and as a result, can outperform stochastic dynamic program (SDP) in terms of adaptability and learning ability
Summary
As the greenhouse effect and air pollution have become increasingly severe, green energy attracts more attention in all walks of life. In [9], a classified rule based EMS is designed, which emphasizes on different operating modes of PHEVs, and simulation results yields satisfied emission reduction. These rule based strategies highly depend on design process and engineering experience, leading to longer design time [11]. In [23], the investigators find that the RL based EMS cannot only guarantee the vehicle dynamic performance, and improve the fuel economy, and as a result, can outperform stochastic dynamic program (SDP) in terms of adaptability and learning ability. In [26], a RL method called TD (λ)-learning is employed for the HEV, and simulation results manifest that the RL based policy can improve the fuel economy by 42%.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
