CroSatFL: Energy-Efficient Federated Learning with Cross-Aggregation for Satellite Edge Computing

2026-04-17

AI Summary

This work addresses the challenges of deploying federated learning in low Earth orbit satellite edge computing, where dynamic network topology, heterogeneous computational capabilities, and stringent energy constraints hinder efficient operation. To overcome these limitations, the authors propose a sustainable on-orbit hierarchical federated learning framework that shifts both model training and intermediate aggregation entirely to satellites, requiring only two ground station communications per round and leveraging inter-satellite laser links for model exchange. Key innovations include StarMask—a heterogeneity-aware clustering mechanism—Skip-One to mitigate straggler effects, and random-k lightweight cross-cluster aggregation. These techniques collectively reduce communication overhead while preserving model accuracy and fairness. Experimental results demonstrate over two orders of magnitude fewer ground communications, approximately sixfold lower transmission energy consumption, and faster convergence with higher accuracy compared to baseline approaches.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Learning to Search
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

Abstract

Low Earth Orbit (LEO) mega-constellations extend the cloud-to-edge continuum into space, enabling satellite edge computing. However, Federated Learning (FL) in this environment is fundamentally energy-constrained due to dynamic inter-satellite connectivity, heterogeneous onboard computing hardware, and strict power budgets. We propose CroSatFL, a sustainable on-orbit hierarchical FL framework that reduces end-to-end energy across computation and communication while maintaining strong training performance under realistic LEO dynamics. CroSatFL keeps the ground station (GS) off the iterative loop by performing all local training and intermediate aggregations on orbit, requiring only two GS communication phases: one for initialization and one for final model collection. This sharply reduces repeated use of bandwidth-limited and energy-expensive GS links and shifts iterative exchanges to laser inter-satellite links (LISLs). CroSatFL integrates three energy-aware mechanisms: StarMask forms LISL-feasible clusters that align data volume with heterogeneous CPU/GPU capability, Skip-One mitigates transient stragglers by skipping at most one slow client per cluster to lower round energy and latency while preserving long-term fairness, and random-k cross-aggregation enables lightweight topology-aware cross-cluster mixing without extending round duration. Using an end-to-end energy model with a realistic Walker-Delta constellation, we show that CroSatFL reduces GS communication count by over two orders of magnitude and GS transmission energy by about 6x relative to GS-centric and on-orbit baselines, while achieving competitive accuracy and faster convergence.

Problem

• Federated Learning
• Satellite Edge Computing
• Energy Efficiency
• Low Earth Orbit
• Inter-satellite Connectivity

Innovation

• Federated Learning
• Satellite Edge Computing
• Energy Efficiency
• Inter-satellite Links
• Hierarchical Aggregation