Federated Learning over Energy Harvesting Wireless Networks

TL;DR

This paper explores federated learning in energy harvesting wireless networks with massive MIMO, proposing joint energy management and user scheduling strategies to optimize training loss and system performance.

Contribution

It introduces a novel joint energy management and user scheduling framework for federated learning over energy harvesting wireless networks, including multiple base stations.

Findings

Proposed algorithms reduce training loss compared to standard FL.

Analytical convergence rate links transmit power and user scheduling to training loss.

Joint user association and scheduling improve system efficiency.

Abstract

In this paper, the deployment of federated learning (FL) is investigated in an energy harvesting wireless network in which the base station (BS) employs massive multiple-input multiple-output (MIMO) to serve a set of users powered by independent energy harvesting sources. Since a certain number of users may not be able to participate in FL due to the interference and energy constraints, a joint energy management and user scheduling problem in FL over wireless systems is formulated. This problem is formulated as an optimization problem whose goal is to minimize the FL training loss via optimizing user scheduling. To find how the factors such as transmit power and number of scheduled users affect the training loss, the convergence rate of the FL algorithm is first analyzed. Given this analytical result, the user scheduling and energy management optimization problem can be decomposed, simplified, and solved. Further, the system model is extended by considering multiple BSs. Hence, a joint user association and scheduling problem in FL over wireless systems is studied. The optimal user association problem is solved using the branch-and-bound technique. Simulation results show that the proposed user scheduling and user association algorithm can reduce training loss compared to a standard FL algorithm.