Research Article
CSA_FedVeh: Cluster-Based Semi-asynchronous Federated Learning Framework for Internet of Vehicles
@INPROCEEDINGS{10.1007/978-3-031-54531-3_5, author={Dun Cao and Jiasi Xiong and Nanfang Lei and Robert Simon Sherratt and Jin Wang}, title={CSA_FedVeh: Cluster-Based Semi-asynchronous Federated Learning Framework for Internet of Vehicles}, proceedings={Collaborative Computing: Networking, Applications and Worksharing. 19th EAI International Conference, CollaborateCom 2023, Corfu Island, Greece, October 4-6, 2023, Proceedings, Part III}, proceedings_a={COLLABORATECOM PART 3}, year={2024}, month={2}, keywords={Internet of vehicles Federated learning Cluster Semi-asynchronous}, doi={10.1007/978-3-031-54531-3_5} }- Dun Cao
Jiasi Xiong
Nanfang Lei
Robert Simon Sherratt
Jin Wang
Year: 2024
CSA_FedVeh: Cluster-Based Semi-asynchronous Federated Learning Framework for Internet of Vehicles
COLLABORATECOM PART 3
Springer
DOI: 10.1007/978-3-031-54531-3_5
Abstract
In Internet of Vehicles (IoV) system, Federated Learning (FL) is a novel distributed approach to processing real-time vehicle data that enables training of shared learning models while ensuring data privacy. However, existing FL still face numerous challenges in IoV. Firstly, the fast convergence with FL models is difficult to achieve due to the high mobility of vehicles and the non-independent identical distribution (Non-IID) among data collected by vehicles. Moreover, the parameter aggregation process of FL incurs significant communication overhead, and the varying computing power of vehicles results in the straggler. To address these issues, this paper proposes a Cluster-based Semi-Asynchronous Federated Learning framework for IoV (CSAFedVeh). Specifically, we propose a Space-Time and Weight DBSCAN density clustering algorithm (STW-DBSCAN) that relies on both the space-time location and model weight similarities of vehicles. Clustering of vehicles can alleviate the impact of Non-IID data, and the joint training of data vehicles can reduce resource consumption and mitigate the straggler effect. In addition, we adopt a semi-asynchronous FL aggregation mechanism to reduce communication time and improve FL efficiency. Experimental results show that compared with baselines under Non-IID datasets, CSAFedVeh can reduce the running time by about 24.6% to 60.2%, and reduce communication consumption by 3.4% to 62.07% on MNIST dataset and 1.01% to 68.6% on GTSRD dataset.
