Optimized Satellite Participation in Federated Learning over LEO Constellation Networks

September 1, 2025·
Madyan Alsenwi
,
Eva Lagunas
,
Jorge Querol
,
Mohammed Al-Ansi
,
Dinh-Hieu Tran
,
Yan Kyaw Tun
,
Symeon Chatzinotas
· 1 min read
Abstract
This paper presents an intelligent device selection framework for Federated Learning (FL) in Low Earth Orbit (LEO) satellite constellation networks. In particular, the high mobility, intermittent connectivity and long communication delays in LEO satellite networks significantly impact FL convergence and model performance. To address these challenges, we formulate a device selection optimization problem that determines the optimal subset of LEO satellites to participate in global model aggregation at each round. The objective is to minimize the average loss while satisfying latency constraints. To solve the formulated problem, we develop a deep reinforcement learning (DRL)-based solution that enables adaptive satellite selection considering the stochastic nature of satellite connectivity and channel variability. The proposed framework selects participating satellites dynamically based on their communication latency and computational capabilities to improve the overall efficiency of the FL process. Simulation results show that the proposed approach accelerates convergence compared to conventional synchronous FL while maintaining model accuracy.
Type
Publication
IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)
publication

Abstract & Overview

This paper presents an intelligent device selection framework for Federated Learning (FL) in Low Earth Orbit (LEO) satellite constellation networks. In particular, the high mobility, intermittent connectivity and long communication delays in LEO satellite networks significantly impact FL convergence and model performance. To address these challenges, we formulate a device selection optimization problem that determines the optimal subset of LEO satellites to participate in global model aggregation at each round. The objective is to minimize the average loss while satisfying latency constraints. To solve the formulated problem, we develop a deep reinforcement learning (DRL)-based solution that enables adaptive satellite selection considering the stochastic nature of satellite connectivity and channel variability. The proposed framework selects participating satellites dynamically based on their communication latency and computational capabilities to improve the overall efficiency of the FL process. Simulation results show that the proposed approach accelerates convergence compared to conventional synchronous FL while maintaining model accuracy.

Publication Metadata

  • Authors: Madyan Alsenwi, Eva Lagunas, Jorge Querol, Mohammed Al-Ansi, Dinh-Hieu Tran, Yan Kyaw Tun, Symeon Chatzinotas
  • Venue: IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) (2025)
  • Research Areas: Satellite Communications
  • DOI: 10.1109/pimrc62392.2025.11275527
  • Open Access Repository: ORBiLu – University of Luxembourg
Satellite Communications