EUVIMEDEUVIMED entdecken
Crossref

GNN-Enhanced Deep Reinforcement Learning for mmWave-NOMA Resource Optimization

Ayman Rabee, Imad Barhumi

IEEE Transactions on Wireless Communications · 2026 · 25 · 17086-17101

DOI: 10.1109/twc.2026.3691272 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Wireless Communications, 2026. Verfasst von Ayman Rabee und 1 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents a unified deep learning framework for resource optimization in millimeter-wave non-orthogonal multiple access (mmWave-NOMA) systems, addressing user clustering, power allocation, and hybrid beamforming. The framework integrates a Graph Neural Network (GNN)-based clustering module with Deep Reinforcement Learning (DRL) architectures. A Graph Attention Network (GAT) is employed to perform adaptive clustering from channel correlations, achieving accurate grouping across diverse network scales with a single trained model that supports dynamic user admission. For resource allocation, standalone and GNN-enhanced Twin Delayed Deep Deterministic Policy Gradient (TD3) models are developed to jointly optimize power and beamforming. Simulation results show that the GNN-based clustering achieves 2–5 ms inference times, compared with 5–70 ms for conventional methods, while the TD3-GNN framework improves spectral efficiency by approximately 13% and enhances power efficiency and quality-of-service satisfaction. The proposed approach offers a scalable and real-time solution for next-generation mmWave-NOMA networks.

Zitieren

APA

Rabee, A., & Barhumi, I. (2026). GNN-Enhanced Deep Reinforcement Learning for mmWave-NOMA Resource Optimization. IEEE Transactions on Wireless Communications, 25, 17086-17101. https://doi.org/10.1109/twc.2026.3691272

Vancouver

Rabee A, Barhumi I. GNN-Enhanced Deep Reinforcement Learning for mmWave-NOMA Resource Optimization. IEEE Transactions on Wireless Communications. 2026;25:17086-17101. doi:10.1109/twc.2026.3691272

BibTeX
@article{Rabee2026,
  author = {Rabee, Ayman and Barhumi, Imad},
  title = {GNN-Enhanced Deep Reinforcement Learning for mmWave-NOMA Resource Optimization},
  journal = {IEEE Transactions on Wireless Communications},
  year = {2026},
  volume = {25},
  pages = {17086--17101},
  doi = {10.1109/twc.2026.3691272}
}
Kostenlos starten →