A GNN Approach for Cell-Free Massive MIMO - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

A GNN Approach for Cell-Free Massive MIMO

Lou Salaun
Hong Yang
  • Fonction : Auteur
Shashwat Mishra
  • Fonction : Auteur
  • PersonId : 1329209
Chung Shue Chen

Résumé

Beyond 5G wireless technology Cell-Free Massive MIMO (CFmMIMO) downlink relies on carefully designed precoders and power control to attain uniformly high rate coverage. Many such power control problems can be calculated via second order cone programming (SOCP). In practice, several order of magnitude faster numerical procedure is required because power control has to be rapidly updated to adapt to changing channel conditions. We propose a Graph Neural Network (GNN) based solution to replace SOCP. Specifically, we develop a GNN to obtain downlink max-min power control for a CFmMIMO with maximum ratio transmission (MRT) beamforming. We construct a graph representation of the problem that properly captures the dominant dependence relationship between access points (APs) and user equipments (UEs). We exploit a symmetry property, called permutation equivariance, to attain training simplicity and efficiency. Simulation results show the superiority of our approach in terms of computational complexity, scalability and generalizability for different system sizes and deployment scenarios.
Fichier principal
Vignette du fichier
main.pdf (536.01 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04443391 , version 1 (07-02-2024)

Identifiants

Citer

Lou Salaun, Hong Yang, Shashwat Mishra, Chung Shue Chen. A GNN Approach for Cell-Free Massive MIMO. GLOBECOM 2022 - 2022 IEEE Global Communications Conference, Dec 2022, Rio de Janeiro, France. pp.3053-3058, ⟨10.1109/GLOBECOM48099.2022.10001647⟩. ⟨hal-04443391⟩

Collections

TDS-MACS
24 Consultations
10 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More