Multi-objective optimization of hybrid electric vehicles energy management using multi-agent deep reinforcement learning framework

被引：0

作者：

Li, Xiaoyu ^{[1
]}

Zhou, Zaihang ^{[1
]}

Wei, Changyin ^{[3
]}

Gao, Xiao ^{[1
]}

Zhang, Yibo ^{[2
]}

机构：

[1] Hebei Univ Technol, Sch Mech Engn, Tianjin 300130, Peoples R China

[2] Beijing Inst Technol, Sch Mech Engn, Beijing 100081, Peoples R China

[3] Hubei Univ Arts & Sci, Hubei Key Lab Power Syst Design & Test Elect Vehic, Xiangyang 441053, Hubei, Peoples R China

来源：

ENERGY AND AI | 2025年 / 20卷

基金：

中国博士后科学基金; 中国国家自然科学基金;

关键词：

Energy management strategy; Hybrid electric vehicle; Reinforcement learning; Multi-agent deep deterministic strategy; gradient; STRATEGY;

D O I：

10.1016/j.egyai.2025.100491

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Hybrid electric vehicles (HEVs) have the advantages of lower emissions and less noise pollution than traditional fuel vehicles. Developing reasonable energy management strategies (EMSs) can effectively reduce fuel consumption and improve the fuel economy of HEVs. However, current EMSs still have problems, such as complex multi-objective optimization and poor algorithm robustness. Herein, a multi-agent reinforcement learning (MADRL) framework is proposed based on Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm to solve such problems. Specifically, a vehicle model and dynamics model are established, and based on this, a multi-objective EMS is developed by considering fuel economy, maintaining the battery State of Charge (SOC), and reducing battery degradation. Secondly, the proposed strategy regards the engine and battery as two agents, and the agents cooperate with each other to realize optimal power distribution and achieve the optimal control strategy. Finally, the WLTC and HWFET driving cycles are employed to verify the performances of the proposed method, the fuel consumption decreases by 26.91 % and 8.41 % on average compared to the other strategies. The simulation results demonstrate that the proposed strategy has remarkable superiority in multi-objective optimization.

引用

页数：11

共 40 条

[1] Tie S.F., Tan C.W., A review of energy sources and energy management system in electric vehicles[J], Renew Sustain Energy Rev, 20, pp. 82-102, (2013)
[2] Sabri M.F.M., Danapalasingam K.A., Rahmat M.F., A review on hybrid electric vehicles architecture and energy management strategies[J], Renew Sustain Energy Rev, 53, pp. 1433-1442, (2016)
[3] Peng S., Zhang H., Yang Y., Et al., Spatial-temporal dynamic forecasting of EVs charging load based on DCC-2D[J], Chin J Electric Eng, 8, 1, pp. 53-62, (2022)
[4] Wang Y., Wu Y., Tang Y., Et al., Cooperative energy management and eco-driving of plug-in hybrid electric vehicle via multi-agent reinforcement learning[J], Appl Energy, 332, (2023)
[5] Gonder J., Markel T., Energy management strategies for plug-in hybrid electric vehicles[R], SAE Techn Paper, (2007)
[6] Uralde J., Barambones O., del Rio A., Et al., Rule-based operation mode control strategy for the energy management of a fuel cell electric vehicle[J], Batteries, 10, 6, (2024)
[7] Li P., Jiao X., Li Y., Adaptive real-time energy management control strategy based on fuzzy inference system for plug-in hybrid electric vehicles[J], Control Eng Pract, 107, (2021)
[8] Zhou S., Chen Z., Huang D., Et al., Model prediction and rule based energy management strategy for a plug-in hybrid electric vehicle with hybrid energy storage system[J], IEEe Trans Power Electron, 36, 5, pp. 5926-5940, (2020)
[9] Tian S., Zheng Q., Wang W., Et al., Integrated real-time optimal energy management strategy for plug-in hybrid electric vehicles based on rule-based strategy and AECMS[J], Int J Vehicle Des, 94, 1-2, pp. 150-175, (2024)
[10] Barelli L., Bidini G., Ciupageanu D.A., Et al., Stochastic power management approach for a hybrid solid oxide fuel cell/battery auxiliary power unit for heavy duty vehicle applications[J], Energy Convers Manage, 221, (2020)

← 1 2 3 4 →