Scalable Multi-User Precoding and Pilot Optimization with Graph Neural Networks

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

3 Zitate (Scopus)

Abstract

We consider the problem of sum rate maximization in frequency division duplex (FDD) systems when only imperfect channel state information (CSI) is available. Inspired by the low complexity and generalization ability offered by graph neural networks (GNNs), we propose an end-to-end (E2E) framework for both, precoding and downlink (DL) pilot sequences optimization based on the novel Edge-graph attention network (GAT). The simulation results confirm the potential of the proposed E2E approach to optimize sum rates and its scalability in scenarios with varying numbers of users. Additionally, the superiority of the learned pilot matrix compared to the conventionally employed sub-discrete Fourier transform (DFT) matrix is highlighted.

OriginalspracheEnglisch
TitelICC 2024 - IEEE International Conference on Communications
Redakteure/-innenMatthew Valenti, David Reed, Melissa Torres
Herausgeber (Verlag)Institute of Electrical and Electronics Engineers Inc.
Seiten2956-2961
Seitenumfang6
ISBN (elektronisch)9781728190549
DOIs
PublikationsstatusVeröffentlicht - 2024
Veranstaltung59th Annual IEEE International Conference on Communications, ICC 2024 - Denver, USA/Vereinigte Staaten
Dauer: 9 Juni 202413 Juni 2024

Publikationsreihe

NameIEEE International Conference on Communications
ISSN (Print)1550-3607

Konferenz

Konferenz59th Annual IEEE International Conference on Communications, ICC 2024
Land/GebietUSA/Vereinigte Staaten
OrtDenver
Zeitraum9/06/2413/06/24

Fingerprint

Untersuchen Sie die Forschungsthemen von „Scalable Multi-User Precoding and Pilot Optimization with Graph Neural Networks“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren