EUVIMEDEUVIMED entdecken
Crossref

Twin-Timescale 3C Resource Allocation for Semantic-Aware Vehicular Edge Computing Using Multi-Agent Graph Reinforcement Learning

Yan Lin, Jinjin Shen, Yijin Zhang, Feng Shu, Chunguo Li, Jun Li

IEEE Transactions on Communications · 2026 · 74 · 11519-11533

DOI: 10.1109/tcomm.2026.3712574 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Communications, 2026. Verfasst von Yan Lin und 5 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Science and Technology Major Project, National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Semantic-aware edge computing has exhibited tremendous potential for reducing communication-computing-caching (3C) resource costs in vehicular networks through task-oriented semantic extraction. However, environmental dynamics and uncertainties across heterogeneous timescales pose critical challenges for 3C resource allocation in semantic-aware vehicular edge computing (VEC) networks. To this end, this paper investigates a joint semantic content caching and semantic task offloading problem in twin-timescale semantic-aware VEC scenarios, aiming to maximize the long-term utility tradeoff between task execution latency and semantic cache hit ratio. First, twin-timescale Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs) are established, where semantic content caching is optimized on a large timescale, while semantic offloading and bandwidth allocation policies are learned on a small timescale. Subsequently, a novel twin-timescale 3C resource allocation solution based on multi-agent graph reinforcement learning method is proposed. Specifically, a Graphical Partial Reward Decoupling-aided Multi-Agent Proximal Policy Optimization (GPRD-MAPPO) algorithm is proposed, which incorporates graph attention networks (GAT) and credit assignment mechanism to decouple the irrelevant agents in cooperative learning by dynamically identifying inter-agent graphical dependencies. Our simulation results verify the superiority of the proposed solution in reducing task execution latency and improving semantic cache hit ratio over the benchmarks in varying numbers of vehicles and diverse task characteristics.

Förderung

  • National Natural Science Foundation of China
  • National Science and Technology Major Project
  • National Key Research and Development Program of China
  • Key Technologies R&D Program of Jiangsu
  • Hainan Province Science and Technology Special Fund
  • Hainan Provincial Natural Science Foundation of China
  • Major Natural Science Foundation of the Higher Education Institutions of Jiangsu Province

Zitieren

APA

Lin, Y., Shen, J., Zhang, Y., Shu, F., Li, C., & Li, J. (2026). Twin-Timescale 3C Resource Allocation for Semantic-Aware Vehicular Edge Computing Using Multi-Agent Graph Reinforcement Learning. IEEE Transactions on Communications, 74, 11519-11533. https://doi.org/10.1109/tcomm.2026.3712574

Vancouver

Lin Y, Shen J, Zhang Y, Shu F, Li C, Li J. Twin-Timescale 3C Resource Allocation for Semantic-Aware Vehicular Edge Computing Using Multi-Agent Graph Reinforcement Learning. IEEE Transactions on Communications. 2026;74:11519-11533. doi:10.1109/tcomm.2026.3712574

BibTeX
@article{Lin2026,
  author = {Lin, Yan and Shen, Jinjin and Zhang, Yijin and Shu, Feng and Li, Chunguo and Li, Jun},
  title = {Twin-Timescale 3C Resource Allocation for Semantic-Aware Vehicular Edge Computing Using Multi-Agent Graph Reinforcement Learning},
  journal = {IEEE Transactions on Communications},
  year = {2026},
  volume = {74},
  pages = {11519--11533},
  doi = {10.1109/tcomm.2026.3712574}
}
Kostenlos starten →