EUVIMEDEUVIMED entdecken
Crossref

Multi-Timescale Reward-Based DRL Energy Management for Regenerative Braking Energy Storage System

Junyu Chen, Yue Zhao, Minghao Wang, Kai Yang, Yinbo Ge, Ke Wang, Hongjian Lin, Pengyu Pan, Haitao Hu, Zhengyou He, Zhao Xu

IEEE Transactions on Transportation Electrification · 2025-06 · 11 (3) · 7488-7500

DOI: 10.1109/tte.2025.3528255 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Transportation Electrification, 2025-06. Verfasst von Junyu Chen und 10 weiteren Autor:innen. Die Arbeit wurde bisher 37-mal zitiert (Crossref) und nennt 35 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Science and Technology Development Fund (FDCT) and Ministry of Science and Technology of China Joint Project, FDCT, Macau, SAR.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The traditional model-based energy management strategy (EMS) for regenerative braking energy storage systems (RBESSs) is obsoleting in the face of increasingly complex and uncertain operation conditions in railway power systems (RPSs). In this article, a model-free deep reinforcement learning (DRL) method is proposed. First, the multiobjective energy management problem for RBESS is formulated to concurrently achieve the regenerative braking energy (RBE) utilization and power demand shaving of RPS. Then, this problem is modeled as a Markov decision process (MDP) to be solved by the DRL-based method. Specifically, the RBESS controller is modeled as an agent to interact with the environment modeled as the RPS integrated with RBESS. To coordinate the agent to learn the optimal strategies regarding multiple energy management objectives in different timescales, a multistage reward function (MSRF) involving the step reward and final reward is designed. Based on the above elements, the double deep Q-learning algorithm is applied to train the agent for optimizing the EMS. Finally, the proposed DRL-based EMS is tested on the OPAL-RT experimental platform by using the field load data. Case studies have demonstrated that the proposed method outperforms the traditional rule-based and optimization-based methods by over 5% in the energy management objective.

Förderung

  • National Natural Science Foundation of China
  • Science and Technology Development Fund (FDCT) and Ministry of Science and Technology of China Joint Project
  • FDCT, Macau, SAR
  • State Key Laboratory of Alternate Electrical Power System With Renewable Energy Sources
  • Sichuan Science and Technology Program
  • Hong Kong Environment and Conservation Fund

Zitieren

APA

Chen, J., Zhao, Y., Wang, M., Yang, K., Ge, Y., Wang, K., Lin, H., Pan, P., Hu, H., He, Z., & Xu, Z. (2025). Multi-Timescale Reward-Based DRL Energy Management for Regenerative Braking Energy Storage System. IEEE Transactions on Transportation Electrification, 11(3), 7488-7500. https://doi.org/10.1109/tte.2025.3528255

Vancouver

Chen J, Zhao Y, Wang M, Yang K, Ge Y, Wang K, et al. Multi-Timescale Reward-Based DRL Energy Management for Regenerative Braking Energy Storage System. IEEE Transactions on Transportation Electrification. 2025;11(3):7488-7500. doi:10.1109/tte.2025.3528255

BibTeX
@article{Chen2025,
  author = {Chen, Junyu and Zhao, Yue and Wang, Minghao and Yang, Kai and Ge, Yinbo and Wang, Ke and Lin, Hongjian and Pan, Pengyu and Hu, Haitao and He, Zhengyou and Xu, Zhao},
  title = {Multi-Timescale Reward-Based DRL Energy Management for Regenerative Braking Energy Storage System},
  journal = {IEEE Transactions on Transportation Electrification},
  year = {2025},
  volume = {11},
  number = {3},
  pages = {7488--7500},
  doi = {10.1109/tte.2025.3528255}
}
Kostenlos starten →