EUVIMEDEUVIMED entdecken
Crossref

GNN-Based Beamforming for Sum-Rate Maximization in MU-MISO Networks

Yuhang Li, Yang Lu, Bo Ai, Octavia A. Dobre, Zhiguo Ding, Dusit Niyato

IEEE Transactions on Wireless Communications · 2024-08 · 23 (8) · 9251-9264

DOI: 10.1109/twc.2024.3361174 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Wireless Communications, 2024-08. Verfasst von Yuhang Li und 5 weiteren Autor:innen. Die Arbeit wurde bisher 52-mal zitiert (Crossref) und nennt 29 Literaturangaben. Gefördert von: China Postdoctoral Science Foundation, National Natural Science Foundation of China, Beijing Nova Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The advantages of graph neural networks (GNNs) in leveraging the graph topology of wireless networks have drawn increasing attentions. This paper studies the GNN-based learning approach for the sum-rate maximization in multiple-user multiple-input single-output (MU-MISO) networks subject to the users’ individual data rate requirements and the power budget of the base station (BS). By modeling the MU-MISO network as a graph, a GNN-based architecture named complex residual graph attention network (CRGAT) is proposed to directly map channel state information to beamforming vectors. The attention-enabled aggregation and the residual-assisted combination are adopted to enhance the learning capability and mitigate the oversmoothing issue. Furthermore, a novel activation function is proposed for the constraint due to the limited power budget at the BS. The CRGAT is trained via unsupervised learning with two proposed loss functions. An evaluation method is proposed for the learning-based approaches, based on which the effectiveness of the proposed CRGAT is validated in comparison with several convex optimization and learning based approaches. Numerical results are provided to reveal the advantages of the CRGAT including the millisecond-level response with limited optimality performance loss, the scalability to different number of users and power budgets, and the adaptability to different system settings.

Förderung

  • China Postdoctoral Science Foundation
  • National Natural Science Foundation of China
  • Beijing Nova Program
  • Natural Sciences and Engineering Research Council of Canada (NSERC) through its Discovery Program

Zitieren

APA

Li, Y., Lu, Y., Ai, B., Dobre, O. A., Ding, Z., & Niyato, D. (2024). GNN-Based Beamforming for Sum-Rate Maximization in MU-MISO Networks. IEEE Transactions on Wireless Communications, 23(8), 9251-9264. https://doi.org/10.1109/twc.2024.3361174

Vancouver

Li Y, Lu Y, Ai B, Dobre OA, Ding Z, Niyato D. GNN-Based Beamforming for Sum-Rate Maximization in MU-MISO Networks. IEEE Transactions on Wireless Communications. 2024;23(8):9251-9264. doi:10.1109/twc.2024.3361174

BibTeX
@article{Li2024,
  author = {Li, Yuhang and Lu, Yang and Ai, Bo and Dobre, Octavia A. and Ding, Zhiguo and Niyato, Dusit},
  title = {GNN-Based Beamforming for Sum-Rate Maximization in MU-MISO Networks},
  journal = {IEEE Transactions on Wireless Communications},
  year = {2024},
  volume = {23},
  number = {8},
  pages = {9251--9264},
  doi = {10.1109/twc.2024.3361174}
}
Kostenlos starten →