Heterogeneity: An Open Challenge for Federated On-board Machine Learning

TL;DR

This paper discusses the challenges of applying Federated Learning to heterogeneous satellite constellations in orbital edge computing, highlighting the need for addressing system heterogeneity in cross-provider collaborations.

Contribution

It provides a systematic review of heterogeneity challenges in federated learning for heterogeneous satellite systems, an area less explored in current research.

Findings

Identifies key heterogeneity challenges in federated learning for satellites.

Summarizes current state-of-the-art solutions for homogeneous systems.

Highlights open issues for cross-provider satellite collaborations.

Abstract

The design of satellite missions is currently undergoing a paradigm shift from the historical approach of individualised monolithic satellites towards distributed mission configurations, consisting of multiple small satellites. With a rapidly growing number of such satellites now deployed in orbit, each collecting large amounts of data, interest in on-board orbital edge computing is rising. Federated Learning is a promising distributed computing approach in this context, allowing multiple satellites to collaborate efficiently in training on-board machine learning models. Though recent works on the use of Federated Learning in orbital edge computing have focused largely on homogeneous satellite constellations, Federated Learning could also be employed to allow heterogeneous satellites to form ad-hoc collaborations, e.g. in the case of communications satellites operated by different providers. Such an application presents additional challenges to the Federated Learning paradigm, arising largely from the heterogeneity of such a system. In this position paper, we offer a systematic review of these challenges in the context of the cross-provider use case, giving a brief overview of the state-of-the-art for each, and providing an entry point for deeper exploration of each issue.