Space for Improvement: Navigating the Design Space for Federated Learning in Satellite Constellations

TL;DR

This paper explores federated learning in satellite constellations, developing space-aware algorithms and a testing platform, leading to a new hierarchical FL method that significantly reduces training time.

Contribution

It introduces a space-specific adaptation of FL algorithms, a novel satellite testing platform, and a hierarchical autonomous FL algorithm with substantial training time improvements.

Findings

AutoFLSat reduces training time by 12.5% to 37.5%.

Developed a space-ification method for FL algorithms.

Created FLySTacK, a satellite constellation testing platform.

Abstract

Space has emerged as an exciting new application area for machine learning, with several missions equipping deep learning capabilities on-board spacecraft. Pre-processing satellite data through on-board training is necessary to address the satellite downlink deficit, as not enough transmission opportunities are available to match the high rates of data generation. To scale this effort across entire constellations, collaborated training in orbit has been enabled through federated learning (FL). While current explorations of FL in this context have successfully adapted FL algorithms for scenario-specific constraints, these theoretical FL implementations face several limitations that prevent progress towards real-world deployment. To address this gap, we provide a holistic exploration of the FL in space domain on several fronts. 1) We develop a method for space-ification of existing FL algorithms, evaluated on 2) FLySTacK, our novel satellite constellation design and hardware aware testing platform where we perform rigorous algorithm evaluations. Finally we introduce 3) AutoFLSat, a generalized, hierarchical, autonomous FL algorithm for space that provides a 12.5% to 37.5% reduction in model training time than leading alternatives.