EUVIMEDEUVIMED entdecken
Crossref

EdgeSAC: Graph Neural Soft Actor-Critic for Hierarchical IoV Resource Management

Arif Raza, Uddin Md. Borhan, Yueling Che, Chen Jie, Lu Wang

IEEE Transactions on Mobile Computing · 2026-09 · 25 (9) · 15014-15026

DOI: 10.1109/tmc.2026.3691088 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-09. Verfasst von Arif Raza und 4 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Shenzhen Science and Technology Innovation Commission, Basic and Applied Basic Research Foundation of Guangdong Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Intelligent Transportation Systems (ITS) rely on the Internet of Vehicles (IoV) to sustain high data rates and low latency under dynamic and heterogeneous conditions. Joint power and spectrum control across macro and micro tiers remains challenging due to mobility, interference coupling, and large continuous action spaces. EdgeSAC is a graph-aware Soft Actor Critic (SAC) framework executed at the edge for power control in hierarchical Fifth-Generation New Radio (5G NR) Multiple-Input Multiple-Output (MIMO) networks. A permutation-equivariant Graph Neural Network (GNN) with edge updates encodes co-channel interference among Base Stations (BSs) and outputs node-level power fractions under tier budgets. An on-demand scheduler activates fixed-size channels and assigns at most one macro and one micro resource per user to realize dual connectivity. Signal-to-Interference-plus-Noise Ratio (SINR) is mapped to rate using a Shannon with gap model with rank adaptive MIMO, enabling tier aggregation without action discretization. In simulation with Third Generation Partnership Project (3GPP) TR 38.901 path loss and Manhattan mobility, EdgeSAC increases throughput over SAC and Proximal Policy Optimization (PPO) and reduces power relative to Twin Delayed Deep Deterministic Policy Gradient (TD3), which raises energy efficiency and fairness. The findings indicate that interference-aware graph embeddings combined with entropy regularized continuous control provide a scalable and power-efficient solution for hierarchical IoV resource management.

Förderung

  • National Natural Science Foundation of China
  • Shenzhen Science and Technology Innovation Commission
  • Basic and Applied Basic Research Foundation of Guangdong Province
  • Shenzhen Science and Technology Program
  • Shenzhen Science and Technology Foundation
  • Key Research and Development Program in Xinjiang Uygur Autonomous Region
  • Guangdong Provincial Key Laboratory of Integrated Communication
  • Sensing and Computation for Ubiquitous IoT

Zitieren

APA

Raza, A., Borhan, U. M., Che, Y., Jie, C., & Wang, L. (2026). EdgeSAC: Graph Neural Soft Actor-Critic for Hierarchical IoV Resource Management. IEEE Transactions on Mobile Computing, 25(9), 15014-15026. https://doi.org/10.1109/tmc.2026.3691088

Vancouver

Raza A, Borhan UM, Che Y, Jie C, Wang L. EdgeSAC: Graph Neural Soft Actor-Critic for Hierarchical IoV Resource Management. IEEE Transactions on Mobile Computing. 2026;25(9):15014-15026. doi:10.1109/tmc.2026.3691088

BibTeX
@article{Raza2026,
  author = {Raza, Arif and Borhan, Uddin Md. and Che, Yueling and Jie, Chen and Wang, Lu},
  title = {EdgeSAC: Graph Neural Soft Actor-Critic for Hierarchical IoV Resource Management},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2026},
  volume = {25},
  number = {9},
  pages = {15014--15026},
  doi = {10.1109/tmc.2026.3691088}
}
Kostenlos starten →