Federated Learning for UAV Swarms Under Class Imbalance and Power Consumption Constraints

TL;DR

This paper explores federated learning for UAV swarms, addressing class imbalance and energy constraints to enhance classification accuracy and operational efficiency without extensive ground communication.

Contribution

It introduces a deployment framework that considers energy and class imbalance, improving UAV swarm performance over baseline methods.

Findings

Improved classification accuracy under energy constraints.

Reduced communication overhead between UAVs and ground.

Enhanced UAV availability and operational efficiency.

Abstract

The usage of unmanned aerial vehicles (UAVs) in civil and military applications continues to increase due to the numerous advantages that they provide over conventional approaches. Despite the abundance of such advantages, it is imperative to investigate the performance of UAV utilization while considering their design limitations. This paper investigates the deployment of UAV swarms when each UAV carries a machine learning classification task. To avoid data exchange with ground-based processing nodes, a federated learning approach is adopted between a UAV leader and the swarm members to improve the local learning model while avoiding excessive air-to-ground and ground-to-air communications. Moreover, the proposed deployment framework considers the stringent energy constraints of UAVs and the problem of class imbalance, where we show that considering these design parameters significantly improves the performances of the UAV swarm in terms of classification accuracy, energy consumption and availability of UAVs when compared with several baseline algorithms.