Energy Management for Electrified Tracked Vehicles via Improved Soft Actor-Critic Algorithm

Qicong Su, Ruchen Huang, Li Kang, Hongwen He*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Energy management strategies (EMSs) play a crucial role in determining the power distribution of hybrid electric vehicles (HEVs). Recently, deep reinforcement learning (DRL) has emerged as a prominent approach for developing EMSs. This paper proposes a DRL-based EMS for a series hybrid electric tracked vehicle (SHETV) equipped with an enginegenerator set (EGS) and a battery pack to improve fuel economy. Firstly, an improved soft actor-critic (SAC) algorithm is formulated by integrating the prioritized experience replay (PER) mechanism. Subsequently, an EMS is developed based on the improved SAC algorithm. Then, a comprehensive evaluation is conducted to assess the superiority of proposed EMS. Extensive comparisons reveal that the proposed EMS achieves a 31.82% faster convergence speed and enhances fuel economy by 4.28% compared to the EMS based on the standard SAC algorithm.

Original languageEnglish
Title of host publication2024 IEEE Vehicle Power and Propulsion Conference, VPPC 2024 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798331541606
DOIs
Publication statusPublished - 2024
Event2024 IEEE Vehicle Power and Propulsion Conference, VPPC 2024 - Washington, United States
Duration: 7 Oct 202410 Oct 2024

Publication series

Name2024 IEEE Vehicle Power and Propulsion Conference, VPPC 2024 - Proceedings

Conference

Conference2024 IEEE Vehicle Power and Propulsion Conference, VPPC 2024
Country/TerritoryUnited States
CityWashington
Period7/10/2410/10/24

Keywords

  • deep reinforcement learning
  • energy management
  • improved soft actor-critic
  • prioritized experience replay
  • series hybrid electric tracked vehicle

Fingerprint

Dive into the research topics of 'Energy Management for Electrified Tracked Vehicles via Improved Soft Actor-Critic Algorithm'. Together they form a unique fingerprint.

Cite this