Improving Communication Efficiency in IoT-based Federated Machine Learning Systems Using Software Defined Networks
Advances in Information, Electronic and Electrical Engineering - Proceedings of the 11th IEEE Workshop, AIEEE 2024 2024
Ints Meijers, Mihails Fraimans, Aigars Riekstiņš

This article focuses on the medical federated machine learning system where clients are portable IoT devices. Currently, multiple limitations complicate the implementation and use of similar systems. In this article, we will address the problem of communication overhead [1] considering the utilization of IoT devices, which typically rely on wireless communication technologies for data transfer, and the size of this data transfer, which usually is larger than double the size of the neural network model being used (might reach hundreds of megabytes). To mitigate the described challenge, we propose a solution based on Software Define Networks, which uses a set of routers and a server. The provided solution will lower the risk of unexpected connection losses and other network errors producing communication overhead in the described system, thus boosting the overall system performance during communication and providing other advantages regarding the quality of the provided communication link.


Keywords
Federated machine learning, Internet of things, Software defined networks
DOI
10.1109/AIEEE62837.2024.10586634

Meijers, I., Fraimans, M., Riekstiņš, A. Improving Communication Efficiency in IoT-based Federated Machine Learning Systems Using Software Defined Networks. In: Advances in Information, Electronic and Electrical Engineering - Proceedings of the 11th IEEE Workshop, AIEEE 2024, Latvia, Valmiera, 31 May-1 Jun., 2024. New York: IEEE, 2024, pp.1-3. e-ISBN 979-8-3315-2776-1. e-ISSN 2689-7342. Available from: doi:10.1109/AIEEE62837.2024.10586634

Publication language
English (en)
The Scientific Library of the Riga Technical University.
E-mail: uzzinas@rtu.lv; Phone: +371 28399196