Federated Learning in UAV-Enhanced Networks: Joint Coverage and Convergence Time Optimization

TL;DR

This paper addresses optimizing UAV placement in wireless sensor networks to enhance federated learning performance by balancing coverage and convergence time, using multi-armed bandit models for decision-making under uncertainty.

Contribution

It introduces a novel multi-objective multi-armed bandit approach for UAV placement that jointly optimizes network coverage and federated learning delay, considering energy constraints.

Findings

The proposed algorithms effectively balance coverage and FL delay.

Numerical results demonstrate improved performance over baseline methods.

The scalarized best-arm identification algorithm reduces energy consumption.

Abstract

Federated learning (FL) involves several devices that collaboratively train a shared model without transferring their local data. FL reduces the communication overhead, making it a promising learning method in UAV-enhanced wireless networks with scarce energy resources. Despite the potential, implementing FL in UAV-enhanced networks is challenging, as conventional UAV placement methods that maximize coverage increase the FL delay significantly. Moreover, the uncertainty and lack of a priori information about crucial variables, such as channel quality, exacerbate the problem. In this paper, we first analyze the statistical characteristics of a UAV-enhanced wireless sensor network (WSN) with energy harvesting. We then develop a model and solution based on the multi-objective multi-armed bandit theory to maximize the network coverage while minimizing the FL delay. Besides, we propose another solution that is particularly useful with large action sets and strict energy constraints at the UAVs. Our proposal uses a scalarized best-arm identification algorithm to find the optimal arms that maximize the ratio of the expected reward to the expected energy cost by sequentially eliminating one or more arms in each round. Then, we derive the upper bound on the error probability of our multi-objective and cost-aware algorithm. Numerical results show the effectiveness of our approach.