Hierarchical Federated Learning in Multi-hop Cluster-Based VANETs
M. Saeid HaghighiFard, Sinem Coleri
TL;DR
This work tackles federated learning in VANETs by introducing a hierarchical FL framework over multi-hop clustered networks, addressing limited bandwidth, high mobility, and non-IID data. It fuses mobility and data similarity into a clustering metric (Avg_CoSim) and implements dynamic cluster-head transitions and CH merging to maintain cluster stability. The HFL algorithm distributes learning across cluster members and CHs with FedAvg-style aggregation, while the EPC performs global aggregation, and a CH-transition mechanism preserves continuity during topology changes. Evaluations using SUMO mobility, MNIST datasets, and Kafka-based data streaming show improved accuracy and faster convergence with manageable overhead compared to non-clustered FL and prior clustering approaches. The approach promises robust, scalable FL deployment in VANETs for real-time sensing, traffic management, and safety-critical applications.
Abstract
The usage of federated learning (FL) in Vehicular Ad hoc Networks (VANET) has garnered significant interest in research due to the advantages of reducing transmission overhead and protecting user privacy by communicating local dataset gradients instead of raw data. However, implementing FL in VANETs faces challenges, including limited communication resources, high vehicle mobility, and the statistical diversity of data distributions. In order to tackle these issues, this paper introduces a novel framework for hierarchical federated learning (HFL) over multi-hop clustering-based VANET. The proposed method utilizes a weighted combination of the average relative speed and cosine similarity of FL model parameters as a clustering metric to consider both data diversity and high vehicle mobility. This metric ensures convergence with minimum changes in cluster heads while tackling the complexities associated with non-independent and identically distributed (non-IID) data scenarios. Additionally, the framework includes a novel mechanism to manage seamless transitions of cluster heads (CHs), followed by transferring the most recent FL model parameter to the designated CH. Furthermore, the proposed approach considers the option of merging CHs, aiming to reduce their count and, consequently, mitigate associated overhead. Through extensive simulations, the proposed hierarchical federated learning over clustered VANET has been demonstrated to improve accuracy and convergence time significantly while maintaining an acceptable level of packet overhead compared to previously proposed clustering algorithms and non-clustered VANET.