Federated Learning-driven Beam Management in LEO 6G Non-Terrestrial Networks

TL;DR

This paper explores federated learning for beam management in LEO satellite networks, demonstrating that graph neural networks outperform traditional models in accuracy and stability, especially at low elevation angles.

Contribution

It introduces a federated learning framework using GNNs for beam selection in LEO NTNs, highlighting its advantages over MLP models in dynamic satellite environments.

Findings

GNN outperforms MLP in beam prediction accuracy.

GNN provides more stable predictions at low elevation angles.

Federated learning enables lightweight, distributed beam management.

Abstract

Low Earth Orbit (LEO) Non-Terrestrial Networks (NTNs) require efficient beam management under dynamic propagation conditions. This work investigates Federated Learning (FL)-based beam selection in LEO satellite constellations, where orbital planes operate as distributed learners through the utilization of High-Altitude Platform Stations (HAPS). Two models, a Multi-Layer Perceptron (MLP) and a Graph Neural Network (GNN), are evaluated using realistic channel and beamforming data. Results demonstrate that GNN surpasses MLP in beam prediction accuracy and stability, particularly at low elevation angles, enabling lightweight and intelligent beam management for future NTN deployments.