On Federated Learning with Energy Harvesting Clients

TL;DR

This paper introduces an energy harvesting federated learning framework that accounts for the random availability of IoT devices due to energy constraints, providing new convergence bounds and practical scheduling insights.

Contribution

It develops novel convergence bounds for EHFL considering device availability variability and proposes a client scheduling strategy to optimize participation.

Findings

Uniform client scheduling improves convergence stability.

Energy harvesting impacts client participation and convergence.

Numerical experiments validate the scheduling strategy's effectiveness.

Abstract

Catering to the proliferation of Internet of Things devices and distributed machine learning at the edge, we propose an energy harvesting federated learning (EHFL) framework in this paper. The introduction of EH implies that a client's availability to participate in any FL round cannot be guaranteed, which complicates the theoretical analysis. We derive novel convergence bounds that capture the impact of time-varying device availabilities due to the random EH characteristics of the participating clients, for both parallel and local stochastic gradient descent (SGD) with non-convex loss functions. The results suggest that having a uniform client scheduling that maximizes the minimum number of clients throughout the FL process is desirable, which is further corroborated by the numerical experiments using a real-world FL task and a state-of-the-art EH scheduler.