IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v16y2023i6p2749-d1098360.html
   My bibliography  Save this article

Influence of the Reward Function on the Selection of Reinforcement Learning Agents for Hybrid Electric Vehicles Real-Time Control

Author

Listed:
  • Matteo Acquarone

    (Interdepartmental Center for Automotive Research and Sustainable Mobility (CARS@PoliTO), Department of Energetics, Politecnico di Torino, Corso Duca degli Abruzzi 24, 10129 Turin, Italy)

  • Claudio Maino

    (Interdepartmental Center for Automotive Research and Sustainable Mobility (CARS@PoliTO), Department of Energetics, Politecnico di Torino, Corso Duca degli Abruzzi 24, 10129 Turin, Italy)

  • Daniela Misul

    (Interdepartmental Center for Automotive Research and Sustainable Mobility (CARS@PoliTO), Department of Energetics, Politecnico di Torino, Corso Duca degli Abruzzi 24, 10129 Turin, Italy)

  • Ezio Spessa

    (Interdepartmental Center for Automotive Research and Sustainable Mobility (CARS@PoliTO), Department of Energetics, Politecnico di Torino, Corso Duca degli Abruzzi 24, 10129 Turin, Italy)

  • Antonio Mastropietro

    (Department of Data Science, EURECOM, Route des Chappes 450, 06904 Biot, France)

  • Luca Sorrentino

    (Addfor Industriale s.r.l., Piazza Solferino 7, 10121 Turin, Italy)

  • Enrico Busto

    (Addfor Industriale s.r.l., Piazza Solferino 7, 10121 Turin, Italy)

Abstract

The real-time control optimization of electrified vehicles is one of the most demanding tasks to be faced in the innovation progress of low-emissions mobility. Intelligent energy management systems represent interesting solutions to solve complex control problems, such as the maximization of the fuel economy of hybrid electric vehicles. In the recent years, reinforcement-learning-based controllers have been shown to outperform well-established real-time strategies for specific applications. Nevertheless, the effects produced by variation in the reward function have not been thoroughly analyzed and the potential of the adoption of a given RL agent under different testing conditions is still to be assessed. In the present paper, the performance of different agents, i.e., Q-learning, deep Q-Network and double deep Q-Network, are investigated considering a full hybrid electric vehicle throughout multiple driving missions and introducing two distinct reward functions. The first function aims at guaranteeing a charge-sustaining policy whilst reducing the fuel consumption (FC) as much as possible; the second function in turn aims at minimizing the fuel consumption whilst ensuring an acceptable battery state of charge (SOC) by the end of the mission. The novelty brought by the results of this paper lies in the demonstration of a non-trivial incapability of DQN and DDQN to outperform traditional Q-learning when a SOC-oriented reward is considered. On the contrary, optimal fuel consumption reductions are attained by DQN and DDQN when more complex FC-oriented minimization is deployed. Such an important outcome is particularly evident when the RL agents are trained on regulatory driving cycles and tested on unknown real-world driving missions.

Suggested Citation

  • Matteo Acquarone & Claudio Maino & Daniela Misul & Ezio Spessa & Antonio Mastropietro & Luca Sorrentino & Enrico Busto, 2023. "Influence of the Reward Function on the Selection of Reinforcement Learning Agents for Hybrid Electric Vehicles Real-Time Control," Energies, MDPI, vol. 16(6), pages 1-22, March.
  • Handle: RePEc:gam:jeners:v:16:y:2023:i:6:p:2749-:d:1098360
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/16/6/2749/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/1996-1073/16/6/2749/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Wu, Yuankai & Tan, Huachun & Peng, Jiankun & Zhang, Hailong & He, Hongwen, 2019. "Deep reinforcement learning of energy management with continuous control strategy and traffic information for a series-parallel plug-in hybrid electric bus," Applied Energy, Elsevier, vol. 247(C), pages 454-466.
    2. Raffaele Cioffi & Marta Travaglioni & Giuseppina Piscitelli & Antonella Petrillo & Fabio De Felice, 2020. "Artificial Intelligence and Machine Learning Applications in Smart Production: Progress, Trends, and Directions," Sustainability, MDPI, vol. 12(2), pages 1-26, January.
    3. Ganesh, Akhil Hannegudda & Xu, Bin, 2022. "A review of reinforcement learning based energy management systems for electrified powertrains: Progress, challenge, and potential solution," Renewable and Sustainable Energy Reviews, Elsevier, vol. 154(C).
    4. Wu, Jingda & He, Hongwen & Peng, Jiankun & Li, Yuecheng & Li, Zhanjiang, 2018. "Continuous reinforcement learning of energy management with deep Q network for a power split hybrid electric bus," Applied Energy, Elsevier, vol. 222(C), pages 799-811.
    5. Maino, Claudio & Misul, Daniela & Musa, Alessia & Spessa, Ezio, 2021. "Optimal mesh discretization of the dynamic programming for hybrid electric vehicles," Applied Energy, Elsevier, vol. 292(C).
    6. Xu, Bin & Rathod, Dhruvang & Zhang, Darui & Yebi, Adamu & Zhang, Xueyu & Li, Xiaoya & Filipi, Zoran, 2020. "Parametric study on reinforcement learning optimized energy management strategy for a hybrid electric vehicle," Applied Energy, Elsevier, vol. 259(C).
    7. Liu, Teng & Wang, Bo & Yang, Chenglang, 2018. "Online Markov Chain-based energy management for a hybrid tracked vehicle with speedy Q-learning," Energy, Elsevier, vol. 160(C), pages 544-555.
    8. Han, Xuefeng & He, Hongwen & Wu, Jingda & Peng, Jiankun & Li, Yuecheng, 2019. "Energy management based on reinforcement learning with double deep Q-learning for a hybrid electric tracked vehicle," Applied Energy, Elsevier, vol. 254(C).
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Daniel Egan & Qilun Zhu & Robert Prucka, 2023. "A Review of Reinforcement Learning-Based Powertrain Controllers: Effects of Agent Selection for Mixed-Continuity Control and Reward Formulation," Energies, MDPI, vol. 16(8), pages 1-31, April.
    2. Yang, Ningkang & Han, Lijin & Xiang, Changle & Liu, Hui & Li, Xunmin, 2021. "An indirect reinforcement learning based real-time energy management strategy via high-order Markov Chain model for a hybrid electric vehicle," Energy, Elsevier, vol. 236(C).
    3. Dong, Peng & Zhao, Junwei & Liu, Xuewu & Wu, Jian & Xu, Xiangyang & Liu, Yanfang & Wang, Shuhan & Guo, Wei, 2022. "Practical application of energy management strategy for hybrid electric vehicles based on intelligent and connected technologies: Development stages, challenges, and future trends," Renewable and Sustainable Energy Reviews, Elsevier, vol. 170(C).
    4. Liu, Teng & Tan, Wenhao & Tang, Xiaolin & Zhang, Jinwei & Xing, Yang & Cao, Dongpu, 2021. "Driving conditions-driven energy management strategies for hybrid electric vehicles: A review," Renewable and Sustainable Energy Reviews, Elsevier, vol. 151(C).
    5. Huang, Ruchen & He, Hongwen & Zhao, Xuyang & Wang, Yunlong & Li, Menglin, 2022. "Battery health-aware and naturalistic data-driven energy management for hybrid electric bus based on TD3 deep reinforcement learning algorithm," Applied Energy, Elsevier, vol. 321(C).
    6. Feng, Zhiyan & Zhang, Qingang & Zhang, Yiming & Fei, Liangyu & Jiang, Fei & Zhao, Shengdun, 2024. "Practicability analysis of online deep reinforcement learning towards energy management strategy of 4WD-BEVs driven by dual-motor in-wheel motors," Energy, Elsevier, vol. 290(C).
    7. Xiao, Boyi & Yang, Weiwei & Wu, Jiamin & Walker, Paul D. & Zhang, Nong, 2022. "Energy management strategy via maximum entropy reinforcement learning for an extended range logistics vehicle," Energy, Elsevier, vol. 253(C).
    8. Hu, Dong & Xie, Hui & Song, Kang & Zhang, Yuanyuan & Yan, Long, 2023. "An apprenticeship-reinforcement learning scheme based on expert demonstrations for energy management strategy of hybrid electric vehicles," Applied Energy, Elsevier, vol. 342(C).
    9. Alessia Musa & Pier Giuseppe Anselma & Giovanni Belingardi & Daniela Anna Misul, 2023. "Energy Management in Hybrid Electric Vehicles: A Q-Learning Solution for Enhanced Drivability and Energy Efficiency," Energies, MDPI, vol. 17(1), pages 1-20, December.
    10. Sun, Alexander Y., 2020. "Optimal carbon storage reservoir management through deep reinforcement learning," Applied Energy, Elsevier, vol. 278(C).
    11. Christian Montaleza & Paul Arévalo & Jimmy Gallegos & Francisco Jurado, 2024. "Enhancing Energy Management Strategies for Extended-Range Electric Vehicles through Deep Q-Learning and Continuous State Representation," Energies, MDPI, vol. 17(2), pages 1-21, January.
    12. Wu, Jingda & Huang, Chao & He, Hongwen & Huang, Hailong, 2024. "Confidence-aware reinforcement learning for energy management of electrified vehicles," Renewable and Sustainable Energy Reviews, Elsevier, vol. 191(C).
    13. Zhang, Hailong & Peng, Jiankun & Tan, Huachun & Dong, Hanxuan & Ding, Fan & Ran, Bin, 2020. "Tackling SOC long-term dynamic for energy management of hybrid electric buses via adaptive policy optimization," Applied Energy, Elsevier, vol. 269(C).
    14. Baodi Zhang & Sheng Guo & Xin Zhang & Qicheng Xue & Lan Teng, 2020. "Adaptive Smoothing Power Following Control Strategy Based on an Optimal Efficiency Map for a Hybrid Electric Tracked Vehicle," Energies, MDPI, vol. 13(8), pages 1-25, April.
    15. Qi, Chunyang & Song, Chuanxue & Xiao, Feng & Song, Shixin, 2022. "Generalization ability of hybrid electric vehicle energy management strategy based on reinforcement learning method," Energy, Elsevier, vol. 250(C).
    16. He, Hongwen & Su, Qicong & Huang, Ruchen & Niu, Zegong, 2024. "Enabling intelligent transferable energy management of series hybrid electric tracked vehicle across motion dimensions via soft actor-critic algorithm," Energy, Elsevier, vol. 294(C).
    17. He, Hongwen & Meng, Xiangfei & Wang, Yong & Khajepour, Amir & An, Xiaowen & Wang, Renguang & Sun, Fengchun, 2024. "Deep reinforcement learning based energy management strategies for electrified vehicles: Recent advances and perspectives," Renewable and Sustainable Energy Reviews, Elsevier, vol. 192(C).
    18. Ye, Yiming & Wang, Hanchen & Xu, Bin & Zhang, Jiangfeng, 2023. "An imitation learning-based energy management strategy for electric vehicles considering battery aging," Energy, Elsevier, vol. 283(C).
    19. Huang, Yin & Kang, Zehao & Mao, Xuping & Hu, Haoqin & Tan, Jiaqi & Xuan, Dongji, 2023. "Deep reinforcement learning based energymanagement strategy considering running costs and energy source aging for fuel cell hybrid electric vehicle," Energy, Elsevier, vol. 283(C).
    20. Han, Lijin & Yang, Ke & Ma, Tian & Yang, Ningkang & Liu, Hui & Guo, Lingxiong, 2022. "Battery life constrained real-time energy management strategy for hybrid electric vehicles based on reinforcement learning," Energy, Elsevier, vol. 259(C).

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jeners:v:16:y:2023:i:6:p:2749-:d:1098360. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.