这份研究论文提出了一种新颖的拓扑感知联邦学习（FL）框架，专为多层卫星网络设计，旨在克服传统星载FL的挑战，如网络动态性和通信链路不稳定性。该框架利用低地球轨道（LEO）卫星进行本地训练，并使用中地球轨道（MEO）和地球静止轨道（GEO）卫星进行分层模型聚合。为了优化聚合路由并减少通信开销和延迟，作者引入了通信高效卫星聚合路由（CESAR）算法，该算法基于图论中的有向最小生成树（DMST）问题。仿真结果表明，与现有方法相比，该框架在学习性能和通信延迟方面均表现出显著的效率。

Topology-Aware Routing for Federated Learning Over Multi-Layer Satellite Networks

Abstract:

Recent advancements in space computing power networks, particularly the integration of onboard computing capabilities in Low Earth Orbit (LEO) satellites, have paved the way for federated learning (FL) in satellite networks. Despite its potential, satellite FL faces unique challenges, such as the dynamic nature of satellite networks and the instability of inter-orbit communication links, which complicate global model aggregation. To address these challenges, we explore FL over multi-layer satellite networks, incorporating LEO, Medium Earth Orbit (MEO), and Geostationary Earth Orbit (GEO) satellites. Specifically, by modeling the dynamic network as a series of time-varying graph snapshots, we propose a novel topology-aware FL framework. To optimize the aggregation routing in the multi-layer satellite network, we leverage the directed minimum spanning tree (DMST) problem in graph theory and introduce a communication-efficient satellite aggregation routing algorithm (CESAR), which effectively reduces communication overhead and aggregation delays, ensuring efficient training and model updates across the satellite network. Extensive experimental results validate the efficacy of the proposed framework, demonstrating its potential to overcome the inherent challenges of satellite FL and significantly advance the capabilities of multi-layer satellite networks.

Published in: 2025 IEEE Wireless Communications and Networking Conference (WCNC)

Date of Conference: 24-27 March 2025

Date Added to IEEE Xplore: 09 May 2025

ISBN Information:

Electronic ISBN:979-8-3503-6836-9

Print on Demand(PoD) ISBN:979-8-3503-6837-6

ISSN Information:

Electronic ISSN: 1558-2612

Print on Demand(PoD) ISSN: 1525-3511

DOI: 10.1109/WCNC61545.2025.10978815

Publisher: IEEE

Conference Location: Milan, Italy

Funding Agency:

10.13039/501100001809-National Nature Science Foundation of China (Grant Number: 62271318)

10.13039/501100018537-China National Science and Technology Major Project (Grant Number: 2022ZD0119102)