TY - JOUR
T1 - Lifespan-consciousness and minimum-consumption coupled energy management strategy for fuel cell hybrid vehicles via deep reinforcement learning
AU - Huo, Weiwei
AU - Chen, Dong
AU - Tian, Sheng
AU - Li, Jianwei
AU - Zhao, Tianyu
AU - Liu, Bo
N1 - Publisher Copyright:
© 2022 Hydrogen Energy Publications LLC
PY - 2022/7/5
Y1 - 2022/7/5
N2 - Energy management strategy (EMS) based on optimized deep reinforcement learning plays a critical role in minimizing fuel consumption and prolonging the fuel cell stack lifespan for fuel cell hybrid vehicles. The deep Q-learning (DQL) and deep deterministic policy gradient (DDPG) algorithms with priority experience replay are proposed in this research. The factors of fuel economy and power fluctuation are incorporated into the multi-objective reward functions to decline the fuel consumption and extend the lifetime of fuel cell stack. In addition, the degradation rate is introduced to reflect the lifetime of fuel cell stack. Furthermore, compared to the referenced optimally energy management strategy (dynamic planning), the DQL-based and DDPG-based EMS with prioritized experience replay (DQL-PER, DDPG-PER) are evaluated in hydrogen consumption and cumulative degradation of fuel cell stack under four driving cycles, FTP75, US06-2, NEDC and LA92-2, respectively. The training results reveal that the DQL-PER-based EMS performances better under FTP75 and US06-2 driving cycles, whereas DDPG-PER-based EMS has better performance under NEDC driving cycle, which provide a potential for applying the proposed algorithm into multi-cycles.
AB - Energy management strategy (EMS) based on optimized deep reinforcement learning plays a critical role in minimizing fuel consumption and prolonging the fuel cell stack lifespan for fuel cell hybrid vehicles. The deep Q-learning (DQL) and deep deterministic policy gradient (DDPG) algorithms with priority experience replay are proposed in this research. The factors of fuel economy and power fluctuation are incorporated into the multi-objective reward functions to decline the fuel consumption and extend the lifetime of fuel cell stack. In addition, the degradation rate is introduced to reflect the lifetime of fuel cell stack. Furthermore, compared to the referenced optimally energy management strategy (dynamic planning), the DQL-based and DDPG-based EMS with prioritized experience replay (DQL-PER, DDPG-PER) are evaluated in hydrogen consumption and cumulative degradation of fuel cell stack under four driving cycles, FTP75, US06-2, NEDC and LA92-2, respectively. The training results reveal that the DQL-PER-based EMS performances better under FTP75 and US06-2 driving cycles, whereas DDPG-PER-based EMS has better performance under NEDC driving cycle, which provide a potential for applying the proposed algorithm into multi-cycles.
KW - DDPG-PER algorithm
KW - DQL-PER algorithm
KW - Energy management strategy
KW - Fuel cell hybrid vehicle
KW - Fuel cell stack lifetime
KW - Minimum fuel consumption
UR - http://www.scopus.com/inward/record.url?scp=85132539410&partnerID=8YFLogxK
U2 - 10.1016/j.ijhydene.2022.05.194
DO - 10.1016/j.ijhydene.2022.05.194
M3 - Article
AN - SCOPUS:85132539410
SN - 0360-3199
VL - 47
SP - 24026
EP - 24041
JO - International Journal of Hydrogen Energy
JF - International Journal of Hydrogen Energy
IS - 57
ER -