Data-driven energy management for electric vehicles using offline reinforcement learning

Abstract Energy management technologies have significant potential to optimize electric vehicle performance and support global energy sustainability. However, despite extensive research, their real-world application remains limited due to reliance on simulations, which often fail to bridge the gap b...

Full description

Saved in:
Bibliographic Details
Main Authors: Yong Wang, Jingda Wu, Hongwen He, Zhongbao Wei, Fengchun Sun
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-025-58192-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849390424629706752
author Yong Wang
Jingda Wu
Hongwen He
Zhongbao Wei
Fengchun Sun
author_facet Yong Wang
Jingda Wu
Hongwen He
Zhongbao Wei
Fengchun Sun
author_sort Yong Wang
collection DOAJ
description Abstract Energy management technologies have significant potential to optimize electric vehicle performance and support global energy sustainability. However, despite extensive research, their real-world application remains limited due to reliance on simulations, which often fail to bridge the gap between theory and practice. This study introduces a real-world data-driven energy management framework based on offline reinforcement learning. By leveraging electric vehicle operation data, the proposed approach eliminates the need for manually designed rules or reliance on high-fidelity simulations. It integrates seamlessly into existing frameworks, enhancing performance after deployment. The method is tested on fuel cell electric vehicles, optimizing energy consumption and reducing system degradation. Real-world data from an electric vehicle monitoring system in China validate its effectiveness. The results demonstrate that the proposed method consistently achieves superior performance under diverse conditions. Notably, with increasing data availability, performance improves significantly, from 88% to 98.6% of the theoretical optimum after two updates. Training on over 60 million kilometers of data enables the learning agent to generalize across previously unseen and corner-case scenarios. These findings highlight the potential of data-driven methods to enhance energy efficiency and vehicle longevity through large-scale vehicle data utilization.
format Article
id doaj-art-602a5cac6c9a4236830b9468c0ff77dc
institution Kabale University
issn 2041-1723
language English
publishDate 2025-03-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj-art-602a5cac6c9a4236830b9468c0ff77dc2025-08-20T03:41:40ZengNature PortfolioNature Communications2041-17232025-03-0116111610.1038/s41467-025-58192-9Data-driven energy management for electric vehicles using offline reinforcement learningYong Wang0Jingda Wu1Hongwen He2Zhongbao Wei3Fengchun Sun4School of Mechanical Engineering, Beijing Institute of TechnologySchool of Mechanical Engineering, Beijing Institute of TechnologySchool of Mechanical Engineering, Beijing Institute of TechnologySchool of Mechanical Engineering, Beijing Institute of TechnologySchool of Mechanical Engineering, Beijing Institute of TechnologyAbstract Energy management technologies have significant potential to optimize electric vehicle performance and support global energy sustainability. However, despite extensive research, their real-world application remains limited due to reliance on simulations, which often fail to bridge the gap between theory and practice. This study introduces a real-world data-driven energy management framework based on offline reinforcement learning. By leveraging electric vehicle operation data, the proposed approach eliminates the need for manually designed rules or reliance on high-fidelity simulations. It integrates seamlessly into existing frameworks, enhancing performance after deployment. The method is tested on fuel cell electric vehicles, optimizing energy consumption and reducing system degradation. Real-world data from an electric vehicle monitoring system in China validate its effectiveness. The results demonstrate that the proposed method consistently achieves superior performance under diverse conditions. Notably, with increasing data availability, performance improves significantly, from 88% to 98.6% of the theoretical optimum after two updates. Training on over 60 million kilometers of data enables the learning agent to generalize across previously unseen and corner-case scenarios. These findings highlight the potential of data-driven methods to enhance energy efficiency and vehicle longevity through large-scale vehicle data utilization.https://doi.org/10.1038/s41467-025-58192-9
spellingShingle Yong Wang
Jingda Wu
Hongwen He
Zhongbao Wei
Fengchun Sun
Data-driven energy management for electric vehicles using offline reinforcement learning
Nature Communications
title Data-driven energy management for electric vehicles using offline reinforcement learning
title_full Data-driven energy management for electric vehicles using offline reinforcement learning
title_fullStr Data-driven energy management for electric vehicles using offline reinforcement learning
title_full_unstemmed Data-driven energy management for electric vehicles using offline reinforcement learning
title_short Data-driven energy management for electric vehicles using offline reinforcement learning
title_sort data driven energy management for electric vehicles using offline reinforcement learning
url https://doi.org/10.1038/s41467-025-58192-9
work_keys_str_mv AT yongwang datadrivenenergymanagementforelectricvehiclesusingofflinereinforcementlearning
AT jingdawu datadrivenenergymanagementforelectricvehiclesusingofflinereinforcementlearning
AT hongwenhe datadrivenenergymanagementforelectricvehiclesusingofflinereinforcementlearning
AT zhongbaowei datadrivenenergymanagementforelectricvehiclesusingofflinereinforcementlearning
AT fengchunsun datadrivenenergymanagementforelectricvehiclesusingofflinereinforcementlearning