IDEAS home Printed from https://ideas.repec.org/a/eee/appene/v409y2026ics030626192600022x.html

An enhanced MADDPG framework for joint energy and QoS optimization in UAV-assisted vehicular edge computing system

Author

Listed:
  • Dai, Cheng
  • Pan, Junqi
  • Liu, Xianggen
  • Garg, Sahil
  • Moussa, Sherif
  • Kandouci, Chahinaz

Abstract

The objective of this study is to address the challenges posed by high energy overhead and the complexity of ensuring quality of service (QoS) for vehicular edge computing in dynamic environments. To this end, this paper investigates the task offloading problem for vehicular edge computing networks in urban areas where there are task offloading hotspots. The objective is twofold: first, to minimize the system energy expenditure, and second, to ensure the service quality. To this end, Unmanned Aerial Vehicles (UAVs) are introduced as mobile offloading nodes to physically reduce the signal transmission distance and lower the system energy consumption. To this end, we propose a resource allocation optimization framework centered on a novel Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm. Our algorithm’s novelty lies in its integration of a dual-critic mechanism for robust and stable Q-value estimation and a maximum entropy framework to enhance exploration efficiency in complex environments. This intelligent algorithm is synergistically coupled with a clustering-based UAV deployment strategy to handle this dynamic problem. This strategy dynamically and autonomously achieves the optimal resource allocation and UAV deployment, with the objective of reducing the system energy overhead and guaranteeing the QoS. Simulation results demonstrate that this framework significantly enhances resource allocation efficiency. Compared to the original MADDPG algorithm, it reduces task costs by 24%, and compared to the fixed offloading position scheme, it reduces task costs by 31.3%. This study offers a valuable reference point and practical insights for reducing energy overhead and optimizing resource allocation in edge computing for vehicular networking.

Suggested Citation

  • Dai, Cheng & Pan, Junqi & Liu, Xianggen & Garg, Sahil & Moussa, Sherif & Kandouci, Chahinaz, 2026. "An enhanced MADDPG framework for joint energy and QoS optimization in UAV-assisted vehicular edge computing system," Applied Energy, Elsevier, vol. 409(C).
    • Handle: RePEc:eee:appene:v:409:y:2026:i:c:s030626192600022x
    DOI: 10.1016/j.apenergy.2026.127370
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S030626192600022X
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.apenergy.2026.127370?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to

    for a different version of it.

    References listed on IDEAS

    as
    1. Niu, Zegong & He, Hongwen, 2024. "A data-driven solution for intelligent power allocation of connected hybrid electric vehicles inspired by offline deep reinforcement learning in V2X scenario," Applied Energy, Elsevier, vol. 372(C).
    2. Abid, Md. Shadman & Apon, Hasan Jamil & Hossain, Salman & Ahmed, Ashik & Ahshan, Razzaqul & Lipu, M.S. Hossain, 2024. "A novel multi-objective optimization based multi-agent deep reinforcement learning approach for microgrid resources planning," Applied Energy, Elsevier, vol. 353(PA).
    3. Lee, Namkyoung & Woo, Joohyun & Kim, Sungryul, 2025. "A deep reinforcement learning ensemble for maintenance scheduling in offshore wind farms," Applied Energy, Elsevier, vol. 377(PA).
    4. Khalatbarisoltani, Arash & Han, Jie & Saeed, Muhammad & Liu, Cong-zhi & Hu, Xiaosong, 2025. "Privacy-preserving integrated thermal and energy management of multi connected hybrid electric vehicles with federated reinforcement learning," Applied Energy, Elsevier, vol. 385(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. Mahmud, Sakib & Sayed, Aya Nabil & Himeur, Yassine & Nhlabatsi, Armstrong & Bensaali, Faycal, 2026. "A comprehensive review of deep reinforcement learning applications from centralized power generation to modern energy internet frameworks," Renewable and Sustainable Energy Reviews, Elsevier, vol. 226(PE).
    2. Zhou, Jianing & Cai, Guowei & Wang, Yibo & Liu, Chuang, 2025. "Dual-timescale scheduling approach for power systems with Energy-intensive loads: Wind power accommodation through forecast deviation decomposition and flexible resource coordination," Energy, Elsevier, vol. 332(C).
    3. He, Wangli & Li, Chengyuan & Cai, Chenhao & Qing, Xiangyun & Du, Wenli, 2024. "Suppressing active power fluctuations at PCC in grid-connection microgrids via multiple BESSs: A collaborative multi-agent reinforcement learning approach," Applied Energy, Elsevier, vol. 373(C).
    4. Yong Fang & Minghao Li & Yunli Yue & Zhonghua Liu, 2024. "Two-Tier Configuration Model for the Optimization of Enterprise Costs and User Satisfaction for Rural Microgrids," Mathematics, MDPI, vol. 12(20), pages 1-19, October.
    5. Azimian, Mahdi & Shen, Xinwei & Gharehpetian, Gevork B., 2025. "Robust scenario-based stochastic expansion planning of multi-carrier microgrids considering incentive-based loans," Applied Energy, Elsevier, vol. 401(PA).
    6. Lee, Namkyoung & Lee, Hyuntae & Joung, Seulgi, 2025. "A wake-induced two-phase planning framework for offshore wind farm maintenance with stochastic mixed-integer program," Applied Energy, Elsevier, vol. 380(C).
    7. Cardo-Miota, Javier & Khadem, Shafi & Bahloul, Mohamed, 2025. "Deep reinforcement learning based electricity bill minimization strategy for residential prosumer," Mathematics and Computers in Simulation (MATCOM), Elsevier, vol. 238(C), pages 296-305.
    8. Wei, Xiaofei & Qian, Yejian & Li, Yao & Yao, Mingyao & Qian, Duode & Gong, Zhen, 2025. "Multi-objective optimization of the TPMS-Fin three-fluid heat exchanger for vehicles using RSM-NSGA-III," Energy, Elsevier, vol. 328(C).
    9. Sun, Ziyi & Guo, Rong & Luo, Maohui, 2025. "Integrated energy-thermal management strategy for range extended electric vehicles based on soft actor-critic under low environment temperature," Energy, Elsevier, vol. 330(C).
    10. Wan, He & Ruan, Jiageng & Xia, Jing & Han, Zexuan & Li, Ying, 2025. "The continuous training of machine learning-based energy management strategy for plug-in hybrid electric vehicle, part I: electric driving mode," Energy, Elsevier, vol. 333(C).
    11. He, Zixiao & Yang, Xudong & Sun, Haiying, 2026. "A review on modeling, simulation and experiment of dynamic wake effect of floating offshore wind turbines," Applied Energy, Elsevier, vol. 406(C).
    12. Guan, Kaifu & Huang, Zhiwu & Gao, Yang & Wu, Yue & Li, Fei & Li, Heng, 2025. "Towards adaptive deep reinforcement learning energy management for electric vehicles: An online updating approach," Energy, Elsevier, vol. 325(C).
    13. Yang, Ting & Xu, Zheming & Ji, Shijie & Liu, Guoliang & Li, Xinhong & Kong, Haibo, 2025. "Cooperative optimal dispatch of multi-microgrids for low carbon economy based on personalized federated reinforcement learning," Applied Energy, Elsevier, vol. 378(PA).
    14. Chen, Zili & Zhou, Ming & Wu, Zhaoyuan & Yang, Linyan & Yue, Hao, 2025. "Attribution analysis to Co-planning renewable energy and storage capacity based on Shapley Additive Explanation," Energy, Elsevier, vol. 325(C).
    15. Jia, Chunchun & Liu, Wei & He, Hongwen & Chau, K.T., 2025. "Health-conscious energy management for fuel cell vehicles: An integrated thermal management strategy for cabin and energy source systems," Energy, Elsevier, vol. 333(C).
    16. Tairo, Derian C. & Silva, Jéssica Alice A. & López, Juan Camilo & Rider, Marcos J., 2025. "Implementation of a microgrid energy management system considering fair EV charging, uncertainties and contingencies: A multi-objective approach," Applied Energy, Elsevier, vol. 396(C).
    17. Panagiotis Michailidis & Iakovos Michailidis & Elias Kosmatopoulos, 2025. "Reinforcement Learning for Electric Vehicle Charging Management: Theory and Applications," Energies, MDPI, vol. 18(19), pages 1-50, October.
    18. Liu, Yiwei & Tang, Yinggan & Hua, Changchun, 2025. "Multi-objective nutcracker optimization algorithm based on fast non-dominated sorting and elite strategy for grid-connected hybrid microgrid system scheduling," Renewable Energy, Elsevier, vol. 242(C).
    19. Lei, Nuo & Zhang, Hao & Hu, Jingjing & Hu, Zunyan & Wang, Zhi, 2025. "Sim-to-real design and development of reinforcement learning-based energy management strategies for fuel cell electric vehicles," Applied Energy, Elsevier, vol. 393(C).
    20. Mahuze, Richard A. & Amadeh, Ali & Yuan, Bo & Zhang, K. Max, 2025. "Collaborative optimization framework for capacity planning of a prosumer-based peer-to-peer electricity trading community," Applied Energy, Elsevier, vol. 384(C).

    More about this item

    Keywords

    ;
    ;
    ;
    ;
    ;

    Statistics

    Access and download statistics

    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:eee:appene:v:409:y:2026:i:c:s030626192600022x. 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: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/description#description .

    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.