EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Task Offloading and Resource Allocation for ICVs in Vehicular Edge Computing Networks Based on Hybrid Hierarchical Deep Reinforcement Learning

Jiahui Liu iD, Yuan Zou, Guodong Du, Xudong Zhang iD, Jinming Wu

Sensors · 12.11.2025 · 25 (22) · 6914

DOI: 10.3390/s25226914 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 12.11.2025. Verfasst von Jiahui Liu und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical Engineering, Beijing Institute of Technology, Beijing 100081, China. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Intelligent connected vehicles (ICVs) face challenges in handling intensive onboard computational tasks due to limited computing capacity. Vehicular edge computing networks (VECNs) offer a promising solution by enabling ICVs to offload tasks to mobile edge computing (MEC), alleviating computational load. As transportation systems are dynamic, vehicular tasks and MEC capacities vary over time, making efficient task offloading and resource allocation crucial. We explored a vehicle–road collaborative edge computing network and formulated the task offloading scheduling and resource allocation problem to minimize the sum of time and energy costs. To address the mixed nature of discrete and continuous decision variables and reduce computational complexity, we propose a hybrid hierarchical deep reinforcement learning (HHDRL) algorithm, structured in two layers. The upper layer of HHDRL enhances the double deep Q-network (DDQN) with a self-attention mechanism to improve feature correlation learning and generates discrete actions (communication decisions), while the lower layer employs deep deterministic policy gradient (DDPG) to produce continuous actions (power control, task offloading, and resource allocation decision). This hybrid design enables efficient decomposition of complex action spaces and improves adaptability in dynamic environments. Results from numerical simulations reveal that HHDRL achieves a significant reduction in total computational cost relative to current benchmark algorithms. Furthermore, the robustness of HHDRL to varying environmental conditions was confirmed by uniformly designing random numbers within a specified range for certain simulation parameters.

Schlagwörter

Stichwörter der Autor:innen

deep reinforcement learningmobile edge computingresource allocationtask offloadingvehicular edge computing networks

Autor:innen und Institutionen

  • School of Mechanical Engineering, Beijing Institute of Technology, Beijing 100081, China.
  • National Engineering Research Center for Electric Vehicles, Beijing Institute of Technology, Beijing 100081, China.
  • Beijing Institute of Technology Chongqing Innovation Center, Chongqing 401100, China.

ORCID-Profile: Jiahui Liu, Xudong Zhang

Förderung

  • National Key R&D Program of China
  • National Natural Science Foundation of China

Zitieren

APA

Liu, J., Zou, Y., Du, G., Zhang, X., & Wu, J. (2025). Task Offloading and Resource Allocation for ICVs in Vehicular Edge Computing Networks Based on Hybrid Hierarchical Deep Reinforcement Learning. Sensors, 25(22), 6914. https://doi.org/10.3390/s25226914

Vancouver

Liu J, Zou Y, Du G, Zhang X, Wu J. Task Offloading and Resource Allocation for ICVs in Vehicular Edge Computing Networks Based on Hybrid Hierarchical Deep Reinforcement Learning. Sensors. 2025;25(22):6914. doi:10.3390/s25226914

BibTeX
@article{Liu2025,
  author = {Liu, Jiahui and Zou, Yuan and Du, Guodong and Zhang, Xudong and Wu, Jinming},
  title = {Task Offloading and Resource Allocation for ICVs in Vehicular Edge Computing Networks Based on Hybrid Hierarchical Deep Reinforcement Learning},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {22},
  pages = {6914},
  doi = {10.3390/s25226914}
}
Kostenlos starten →