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.
@article{arxiv.2603.10983,
title = {Federated Learning-driven Beam Management in LEO 6G Non-Terrestrial Networks},
author = {Maria Lamprini Bartsioka and Ioannis A. Bartsiokas and Athanasios D. Panagopoulos and Dimitra I. Kaklamani and Iakovos S. Venieris},
journal= {arXiv preprint arXiv:2603.10983},
year = {2026}
}
Comments
2 pages with 2 figures and 1 table. Accepted in 2026 International Applied Computational Electromagnetics Society (ACES) Symposium