Parameter Prioritization for Efficient Transmission of Neural Networks in Small Satellite Applications
Key: KDLS-1
Author: Olga Kondrateva, Stefan Dietzel, Ansgar Lößer, Björn Scheuermann
Date: 2023
Kind: In proceedings
Publisher: IEEE
Book title: Proceedings of the 21st Mediterranean Communication and Computer Networking Conference (MedComNet)
Abstract: Low-earth-orbit (LEO) satellites can be used to launch cost-effective Earth observation missions. Onboard processing, in particular using machine learning (ML) approaches, is often discussed as a way to reduce the amount of data transmitted back to Earth. However, the combination of LEO satellites and ML brings unique communication challenges, as requirements - and therefore ML models - often change throughout the lifetime of a satellite mission. In this paper, we propose a novel communication protocol that deals with model updates efficiently by providing incremental updates with low communication overhead and quick improvements in onboard classification accuracy. Our initial evaluation shows that the proposed, priority-based approach significantly outperforms the baseline of transmitting updated models without considering prioritization.

The documents distributed by this server have been provided by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a non-commercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, not withstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.