Wirelessly Powered Federated Edge Learning: Optimal Tradeoffs Between Convergence and Power Transfer
Qunsong Zeng, Yuqing Du, Kaibin Huang
Abstract
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Federated edge learning</i> (FEEL) is a widely adopted framework for training an <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">artificial intelligence</i> (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 <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">wireless power transfer</i> (WPT). To derive guidelines on deploying the resultant <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">wirelessly powered FEEL</i> (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 yield a guaranteer on learning performance. They are corroborated by experimental results using a real dataset.