descriptionPublicationkeyboard_double_arrow_right Article , Other literature type , Preprint 01 Oct 2023Embargo end date: 01 Jan 2023 Finland Publisher:Institute of Electrical and Electronics Engineers (IEEE)Journal:IEEE Communications Letters, volume 27, pages 2,867-2,871 (issn: 1089-7798, eissn: 2373-7891,

Authors: Rafael Valente da Silva; Onel L. Alcaraz López; Richard Demo Souza;

doi: 10.1109/lcomm.2023.3312793 , 10.48550/arxiv.2309.06033 , 10.60692/4ffmj-bcz09 , 10.60692/mcc6f-rnr91

arXiv: http://arxiv.org/abs/2309.06033

Energy-Aware Federated Learning With Distributed User Sampling and Multichannel ALOHA

- Summary
- Subjects
- Metrics

Abstract

Distributed learning on edge devices has attracted increased attention with the advent of federated learning (FL). Notably, edge devices often have limited battery and heterogeneous energy availability, while multiple rounds are required in FL for convergence, intensifying the need for energy efficiency. Energy depletion may hinder the training process and the efficient utilization of the trained model. To solve these problems, this letter considers the integration of energy harvesting (EH) devices into a FL network with multi-channel ALOHA, while proposing a method to ensure both low energy outage probability and successful execution of future tasks. Numerical results demonstrate the effectiveness of this method, particularly in critical setups where the average energy income fails to cover the iteration cost. The method outperforms a norm based solution in terms of convergence time and battery level.

Country

Finland

Related Organizations

Universidade Federal de Santa Catarina
Brazil
University of Oulu
Finland

Keywords

Signal Processing (eess.SP), FOS: Computer and information sciences, Computer Science - Machine Learning, Energy Efficiency, Economics, Wireless Energy Harvesting and Information Transfer, FOS: Mechanical engineering, Optimizing Information Freshness in Communication Networks, Machine Learning (cs.LG), Engineering, Efficient energy use, Aloha, Computer network, Energy harvesting, Statistics, Privacy-Preserving Techniques for Data Analysis and Machine Learning, Mechanical engineering, Enhanced Data Rates for GSM Evolution, Physical Sciences, Convergence (economics), Wireless, Telecommunications, Computer Networks and Communications, Computer Science - Information Theory, Wireless Energy Harvesting, Edge device, Artificial Intelligence, Energy Harvesting, FOS: Mathematics, FOS: Electrical engineering, electronic engineering, information engineering, Cloud computing, Cover (algebra), Electrical Engineering and Systems Science - Signal Processing, Electrical and Electronic Engineering, Economic growth, Information Theory (cs.IT), Computer science, Throughput, Distributed computing, Process (computing), Operating system, Electrical engineering, Computer Science, RF Energy Harvesting, Energy (signal processing), Federated Learning, Mathematics

Impact byBIP!

	selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	2
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Average
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Average
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Average