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

TL;DR

This paper proposes an energy-efficient federated learning framework integrating energy harvesting devices and multi-channel ALOHA, improving convergence time and battery management in energy-constrained edge networks.

Contribution

It introduces a novel method combining energy harvesting and multi-channel ALOHA to enhance energy efficiency and task success in federated learning on edge devices.

Findings

Method reduces energy outage probability.

Outperforms norm-based solutions in convergence time.

Maintains higher battery levels during training.

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.