EUVIMEDEUVIMED entdecken
Crossref

A Hierarchical and Entropy‐Adaptive Reinforcement Learning Framework for Multi‐Task Offloading in Vehicular Ad Hoc Networks

Min Wang, Huimin Guo, Cong Liu, Mohammad Shabaz, Hamad Aldawsari, Sibo Qiao

Transactions on Emerging Telecommunications Technologies · 2026-06 · 37 (6)

DOI: 10.1002/ett.70454 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Transactions on Emerging Telecommunications Technologies, online erschienen am 25.05.2026. Verfasst von Min Wang und 5 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundação para a Ciência e a Tecnologia.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In dynamic vehicular ad hoc networks (VANETs), high vehicle mobility and time varying communication links make task offloading highly uncertain. As the numbers of vehicles and tasks increase, the joint decision space grows rapidly under this uncertainty, which further complicates offloading optimization. Traditional reinforcement learning methods therefore often suffer from action‐space explosion and unstable convergence. To address this issue, we propose a hierarchical task‐enhanced fully decentralized multi‐agent proximal policy optimization method (HT‐FMPPO), which integrates a hierarchical reinforcement scheduling framework (HRS) and a target entropy driven adaptive entropy regularization mechanism (TEAR). The HRS decomposes joint offloading into batch level quota planning and task level execution location selection, thereby reducing decision complexity in large action spaces. The TEAR adjusts the entropy coefficient online based on the gap between current policy entropy and target policy entropy, thereby improving exploration in early training and reducing excessive randomness during convergence. The experimental results show that HT‐FMPPO reduces request completion time and total energy consumption across different vehicle and task scales, while achieving better convergence and stability.

Förderung

  • National Natural Science Foundation of China
  • Fundação para a Ciência e a Tecnologia

Zitieren

APA

Wang, M., Guo, H., Liu, C., Shabaz, M., Aldawsari, H., & Qiao, S. (2026). A Hierarchical and Entropy‐Adaptive Reinforcement Learning Framework for Multi‐Task Offloading in Vehicular Ad Hoc Networks. Transactions on Emerging Telecommunications Technologies, 37(6). https://doi.org/10.1002/ett.70454

Vancouver

Wang M, Guo H, Liu C, Shabaz M, Aldawsari H, Qiao S. A Hierarchical and Entropy‐Adaptive Reinforcement Learning Framework for Multi‐Task Offloading in Vehicular Ad Hoc Networks. Transactions on Emerging Telecommunications Technologies. 2026;37(6). doi:10.1002/ett.70454

BibTeX
@article{Wang2026,
  author = {Wang, Min and Guo, Huimin and Liu, Cong and Shabaz, Mohammad and Aldawsari, Hamad and Qiao, Sibo},
  title = {A Hierarchical and Entropy‐Adaptive Reinforcement Learning Framework for Multi‐Task Offloading in Vehicular Ad Hoc Networks},
  journal = {Transactions on Emerging Telecommunications Technologies},
  year = {2026},
  volume = {37},
  number = {6},
  doi = {10.1002/ett.70454}
}
Kostenlos starten →