Distributed Inferencing and Federated Learning, for Distributed-edge-AI Miniaturised Satellite Constellations

Abstract

In this research, we report the deployment of a networked space-edge-AI test bed that is analogous to the behaviour of a real satellite constellation and incorporates actual edge AI hardware. We demonstrate the implementation of federated learning on the AI test bed, outline the AI test bed system architecture, and conduct a preliminary study to assess the AI models performances in performing image classification on the AI test bed. The result of this preliminary study serves as a proof-of-concept which demonstrates the feasibility of applying federated learning for a constellation of miniaturised satellites to improve satellites AI capabilities.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 28, 2024
Accession Number
AD1229993

Entities

People

  • Russell Boyce

Organizations

  • University of New South Wales

Tags

Readers

  • Aerospace Engineering.
  • Artificial Intelligence
  • Distributed Systems and Data Platform Development

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy
  • AI & ML - Neural Networks
  • Space
  • Space - Satellites