Graph Neural Network for Location- and Orientation-Assisted mmWave Beam Alignment

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lei, Yuzhu, Xiao, Qiqi, He, Yinghui, Yu, Guanding
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915737189220352
author Lei, Yuzhu
Xiao, Qiqi
He, Yinghui
Yu, Guanding
author_facet Lei, Yuzhu
Xiao, Qiqi
He, Yinghui
Yu, Guanding
contents In massive multi-input multi-output (MIMO) systems, the main bottlenecks of location- and orientation-assisted beam alignment using deep neural networks (DNNs) are large training overhead and significant performance degradation. This paper proposes a graph neural network (GNN)-based beam selection approach that reduces the training overhead and improves the alignment accuracy, by capitalizing on the strong expressive ability and few trainable parameters of GNN. The channels of beams are correlated according to the beam direction. Therefore, we establish a graph according to the angular correlation between beams and use GNN to capture the channel correlation between adjacent beams, which helps accelerate the learning process and enhance the beam alignment performance. Compared to existing DNN-based algorithms, the proposed method requires only 20\% of the dataset size to achieve equivalent accuracy and improves the Top-1 accuracy by 10\% when using the same dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2503_06943
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Graph Neural Network for Location- and Orientation-Assisted mmWave Beam Alignment
Lei, Yuzhu
Xiao, Qiqi
He, Yinghui
Yu, Guanding
Signal Processing
In massive multi-input multi-output (MIMO) systems, the main bottlenecks of location- and orientation-assisted beam alignment using deep neural networks (DNNs) are large training overhead and significant performance degradation. This paper proposes a graph neural network (GNN)-based beam selection approach that reduces the training overhead and improves the alignment accuracy, by capitalizing on the strong expressive ability and few trainable parameters of GNN. The channels of beams are correlated according to the beam direction. Therefore, we establish a graph according to the angular correlation between beams and use GNN to capture the channel correlation between adjacent beams, which helps accelerate the learning process and enhance the beam alignment performance. Compared to existing DNN-based algorithms, the proposed method requires only 20\% of the dataset size to achieve equivalent accuracy and improves the Top-1 accuracy by 10\% when using the same dataset.
title Graph Neural Network for Location- and Orientation-Assisted mmWave Beam Alignment
topic Signal Processing
url https://arxiv.org/abs/2503.06943