Simultaneous Wireless Information and Power Transfer for Federated Learning

TL;DR

This paper explores how simultaneous wireless information and power transfer can optimize federated learning in IoT devices, balancing energy harvesting and communication efficiency to improve learning speed and accuracy.

Contribution

It introduces an optimization framework for federated learning with wireless power transfer, analyzing trade-offs and demonstrating the effectiveness of beamforming techniques.

Findings

Maximum ratio transmission improves test accuracy.

Zero-forcing beamforming enhances local iteration efficiency.

Wireless power transfer enables quick learning with minimal battery depletion.

Abstract

In the Internet of Things, learning is one of most prominent tasks. In this paper, we consider an Internet of Things scenario where federated learning is used with simultaneous transmission of model data and wireless power. We investigate the trade-off between the number of communication rounds and communication round time while harvesting energy to compensate the energy expenditure. We formulate and solve an optimization problem by considering the number of local iterations on devices, the time to transmit-receive the model updates, and to harvest sufficient energy. Numerical results indicate that maximum ratio transmission and zero-forcing beamforming for the optimization of the local iterations on devices substantially boost the test accuracy of the learning task. Moreover, maximum ratio transmission instead of zero-forcing provides the best test accuracy and communication round time trade-off for various energy harvesting percentages. Thus, it is possible to learn a model quickly with few communication rounds without depleting the battery.