Deep reinforcement learning-based energy management of hybrid battery systems in electric vehicles

被引：124

作者：

Li, Weihan ^{[1
,2
]}

Cui, Han ^{[1
]}

Nemeth, Thomas ^{[1
,2
]}

Jansen, Jonathan ^{[1
]}

Uenluebayir, Cem ^{[1
,2
]}

Wei, Zhongbao ^{[4
]}

Zhang, Lei ^{[4
]}

Wang, Zhenpo ^{[4
]}

Ruan, Jiageng ^{[5
]}

Dai, Haifeng ^{[6
]}

Wei, Xuezhe ^{[6
]}

Sauer, Dirk Uwe ^{[1
,2
,3
]}

机构：

[1] Rhein Westfal TH Aachen, Inst Power Elect & Elect Drives ISEA, Chair Electrochem Energy Convers & Storage Syst, Jaegerstr 17-19, D-52066 Aachen, Germany

[2] JARA Energy, Juelich Aachen Res Alliance, Julich, Germany

[3] Forschungszentrum Julich, Helmholtz Inst Munster HI MS, IEK 12, Julich, Germany

[4] Beijing Inst Technol, Sch Mech Engn, Natl Engn Lab Elect Vehicles, Beijing, Peoples R China

[5] Beijing Univ Technol, Fac Mat & Mfg, Beijing, Peoples R China

[6] Tongji Univ, Sch Automot Studies, Natl Fuel Cell Vehicle & Powertrain Syst Res & En, Shanghai, Peoples R China

来源：

JOURNAL OF ENERGY STORAGE | 2021年 / 36卷

关键词：

Lithium-ion battery; Hybrid battery system; Reinforcement learning; Deep Q-learning; Energy management; Electric vehicle; POWER MANAGEMENT; OPTIMIZATION; STRATEGY;

D O I：

10.1016/j.est.2021.102355

中图分类号：

TE [石油、天然气工业]; TK [能源与动力工程];

学科分类号：

0807 ; 0820 ;

摘要：

In this paper, we propose an energy management strategy based on deep reinforcement learning for a hybrid battery system in electric vehicles consisting of a high-energy and a high-power battery pack. The energy management strategy of the hybrid battery system was developed based on the electrical and thermal characterization of the battery cells, aiming at minimizing the energy loss and increasing both the electrical and thermal safety level of the whole system. Primarily, we designed a novel reward term to explore the optimal operating range of the high-power pack without imposing a rigid constraint of state of charge. Furthermore, various load profiles were randomly combined to train the deep Q-learning model, which avoided the overfitting problem. The training and validation results showed both the effectiveness and reliability of the proposed strategy in loss reduction and safety enhancement. The proposed energy management strategy has demonstrated its superiority over the reinforcement learning-based methods in both computation time and energy loss reduction of the hybrid battery system, highlighting the use of such an approach in future energy management systems.

引用

页数：11

共 53 条

[1]

[Anonymous], 1989, PHD DISSERTATION

[2]

Becker Jan., 2018, World Electric Vehicle Journal, V9, P19, DOI DOI 10.3390/WEVJ9020019

[3] Real-Time Optimal Energy Management of Electrified Powertrains with Reinforcement Learning [J].