EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Dynamic Allocation of C-V2X Communication Resources Based on Graph Attention Network and Deep Reinforcement Learning

Zhijuan Li iD, Guohong Li iD, Zhuofei Wu iD, Wei Zhang iD, Alessandro Bazzi iD

Sensors · 21.08.2025 · 25 (16) · 5209

DOI: 10.3390/s25165209 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 21.08.2025. Verfasst von Zhijuan Li und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer and Big Data, Heilongjiang University, Harbin 150080, China. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Basic Scientific Research Funds of Universities of Heilongjiang Province, Heilongjiang Province Postdoctoral Fund.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Vehicle-to-vehicle (V2V) and vehicle-to-network (V2N) communications are two key components of intelligent transport systems (ITSs) that can share spectrum resources through in-band overlay. V2V communication primarily supports traffic safety, whereas V2N primarily focuses on infotainment and information exchange. Achieving reliable V2V transmission alongside high-rate V2N services in resource-constrained, dynamically changing traffic environments poses a significant challenge for resource allocation. To address this, we propose a novel reinforcement learning (RL) framework, termed Graph Attention Network (GAT)-Advantage Actor–Critic (GAT-A2C). In this framework, we construct a graph based on V2V links and their potential interference relationships. Each V2V link is represented as a node, and edges connect nodes that may interfere. The GAT captures key interference patterns among neighboring vehicles while accounting for real-time mobility and channel variations. The features generated by the GAT, combined with individual link characteristics, form the environment state, which is then processed by the RL agent to jointly optimize the resource blocks allocation and the transmission power for both V2V and V2N communications. Simulation results demonstrate that the proposed method substantially improves V2N rates and V2V communication success ratios under various vehicle densities. Furthermore, the approach exhibits strong scalability, making it a promising solution for future large-scale intelligent vehicular networks operating in dynamic traffic scenarios.

Schlagwörter

Stichwörter der Autor:innen

advantage actor–criticdynamic vehicular networksgraph attention networksreinforcement learningvehicle-to-vehicle

Autor:innen und Institutionen

  • School of Computer and Big Data, Heilongjiang University, Harbin 150080, China.
  • Postdoctoral Program of Heilongjiang Hengxun Technology Co., Ltd., Xuefu Road, Harbin 150090, China.
  • Shandong Hengxun Technology Co., Ltd., Miaoling Road, Qingdao 266100, China.
  • Department of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China.
  • WiLab, CNIT/DEI, University of Bologna, 40136 Bologna, Italy.

ORCID-Profile: Zhijuan Li, Guohong Li, Zhuofei Wu, Wei Zhang, Alessandro Bazzi

Förderung

  • Basic Scientific Research Funds of Universities of Heilongjiang Province
  • Heilongjiang Province Postdoctoral Fund

Zitieren

APA

Li, Z., Li, G., Wu, Z., Zhang, W., & Bazzi, A. (2025). Dynamic Allocation of C-V2X Communication Resources Based on Graph Attention Network and Deep Reinforcement Learning. Sensors, 25(16), 5209. https://doi.org/10.3390/s25165209

Vancouver

Li Z, Li G, Wu Z, Zhang W, Bazzi A. Dynamic Allocation of C-V2X Communication Resources Based on Graph Attention Network and Deep Reinforcement Learning. Sensors. 2025;25(16):5209. doi:10.3390/s25165209

BibTeX
@article{Li2025,
  author = {Li, Zhijuan and Li, Guohong and Wu, Zhuofei and Zhang, Wei and Bazzi, Alessandro},
  title = {Dynamic Allocation of C-V2X Communication Resources Based on Graph Attention Network and Deep Reinforcement Learning},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {16},
  pages = {5209},
  doi = {10.3390/s25165209}
}
Kostenlos starten →