Latency Minimization for UAV-Enabled Federated Learning: Trajectory Design and Resource Allocation

TL;DR

This paper introduces a UAV-assisted federated learning framework that optimizes trajectory and resource allocation to minimize latency and improve training efficiency over wireless IoT networks.

Contribution

It proposes a novel joint optimization approach for UAV trajectory, bandwidth, power, and computing resources to enhance FL performance and reduce latency.

Findings

Latency reduced by up to 15.29% compared to benchmarks

Achieves near-ideal training efficiency

Develops an efficient alternating optimization algorithm

Abstract

Federated learning (FL) has become a transformative paradigm for distributed machine learning across wireless networks. However, the performance of FL is often hindered by the unreliable communication links between resource-constrained Internet of Things (IoT) devices and the central server. To overcome this challenge, we propose a novel framework that employs an unmanned aerial vehicle (UAV) as a mobile server to enhance the FL training process. By capitalizing on the UAV's mobility, we establish strong line-of-sight connections with IoT devices, thereby enhancing communication reliability and capacity. To maximize training efficiency, we formulate a latency minimization problem that jointly optimizes bandwidth allocation, computing frequencies, transmit power for both the UAV and IoT devices, and the UAV's flight trajectory. Subsequently, we analyze the required rounds of the IoT devices training and the UAV aggregation for FL convergence. Based on the convergence constraint, we transform the problem into three subproblems and develop an efficient alternating optimization algorithm to solve this problem effectively. Additionally, we provide a thorough analysis of the algorithm's convergence and computational complexity. Extensive numerical results demonstrate that our proposed scheme not only surpasses existing benchmark schemes in reducing latency up to 15.29%, but also achieves training efficiency that nearly matches the ideal scenario.