Hierarchical Federated Learning for Edge-Aided Unmanned Aerial Vehicle Networks

Abstract

Federated learning (FL) allows UAVs to collaboratively train a globally shared machine learning model while locally preserving their private data. Recently, the FL in edge-aided unmanned aerial vehicle (UAV) networks has drawn an upsurge of research interest due to a bursting increase in heterogeneous data acquired by UAVs and the need to build the global model with privacy; however, a critical issue is how to deal with the non-independent and identically distributed (non-i.i.d.) nature of heterogeneous data while ensuring the convergence of learning. To effectively address this challenging issue, this paper proposes a novel and high-performing FL scheme, namely, the hierarchical FL algorithm, for the edge-aided UAV network, which exploits the edge servers located in base stations as intermediate aggregators with employing commonly shared data. Experiment results demonstrate that the proposed hierarchical FL algorithm outperforms several baseline FL algorithms and exhibits better convergence behavior.

Resource Allocation Technique among Mobile Virtual VCN operators

“…In 2022, Jamshid Tursunboev propose federated learning approach for the unmanned aerial vehicles. Simulation result shows that it has a better performance as compared to other technique [15]. In 2021, Vartika Agarwal discuss about network resource management technique in Vehicular network [16].…”

A Comprehensive Survey on 5G-and-Beyond Networks With UAVs: Applications, Emerging Technologies, Regulatory Aspects, Research Trends and Challenges

“…A critical challenge arises from handling the nonindependent and non-identically distributed nature of heterogeneous data while ensuring learning convergence. To effectively tackle this issue, a novel and high-performance federated learning scheme, referred to as the hierarchical federated learning algorithm, is introduced in [184] for the edge-assisted UAV network. This approach leverages edge servers positioned in BSs as intermediate aggregators, incorporating commonly shared data to address the challenge effectively.…”

A Survey on Fault Detection in Industrial IoT: A Machine Learning Approach with Emphasis on Federated Learning and Intrusion Detection Systems

“…The machines are categorized into several clusters based on the departments they belong to in the warehouse, such as transportation, production, packaging, external feedback, and others. Furthermore, the classi cation of devices in a working area might be determined not only by their respective work areas, but also by the speci c tasks they have been allocated.HFL provides a promising solution to the heterogeneity challenge and enables multitask learning [19]. HFL enables the division of Federated Learning tasks into multiple phases, resulting in improved resource man-agement and a more precise global model.…”