Wirelessly Powered Federated Edge Learning: Optimal Tradeoffs Between Convergence and Power Transfer

TL;DR

This paper explores the optimal balance between wireless power transfer and model convergence in federated edge learning, providing analytical guidelines for deploying wireless power sources to enhance energy efficiency and learning performance.

Contribution

It introduces a comprehensive analytical framework for wirelessly powered federated edge learning, deriving tradeoffs between power transfer settings and convergence, and optimizing device computation for energy efficiency.

Findings

Scaling laws of convergence rate with transferred energy

Guidelines for WPT deployment to guarantee learning performance

Optimized local computation parameters for energy-efficient gradient estimation

Abstract

Federated edge learning (FEEL) is a widely adopted framework for training an artificial intelligence (AI) model distributively at edge devices to leverage their data while preserving their data privacy. The execution of a power-hungry learning task at energy-constrained devices is a key challenge confronting the implementation of FEEL. To tackle the challenge, we propose the solution of powering devices using wireless power transfer (WPT). To derive guidelines on deploying the resultant wirelessly powered FEEL (WP-FEEL) system, this work aims at the derivation of the tradeoff between the model convergence and the settings of power sources in two scenarios: 1) the transmission power and density of power-beacons (dedicated charging stations) if they are deployed, or otherwise 2) the transmission power of a server (access-point). The development of the proposed analytical framework relates the accuracy of distributed stochastic gradient estimation to the WPT settings, the randomness in both communication and WPT links, and devices' computation capacities. Furthermore, the local-computation at devices (i.e., mini-batch size and processor clock frequency) is optimized to efficiently use the harvested energy for gradient estimation. The resultant learning-WPT tradeoffs reveal the simple scaling laws of the model-convergence rate with respect to the transferred energy as well as the devices' computational energy efficiencies. The results provide useful guidelines on WPT provisioning to provide a guaranteer on learning performance. They are corroborated by experimental results using a real dataset.