Efficient Information Dissemination in Blockchain-Enabled Federated Learning for IoV

With the rise of smart vehicles, an intelligent transportation system intelligent transport system (ITS) learning from the tremendous volume of the data generated by the distributed vehicles is becoming a reality. blockchain (BC)-based federated learning (FL) facilities a highly secure and trustless collaborative learning framework; however, it could be inefficient for the time-sensitive services of the Internet of Vehicles (IoV). In this regard, this study investigates information dissemination delay in BC-based FL for IoV using a small world network-based peer selection strategy. Additionally, we also incorporate IoV specific informed decision for peer selection to facilitate even faster dissemination of information in the network and make BC-based system efficient. Network topology of vehicles is represented using a graph approach and based on that the information dissemination delay is formulated. The delay is compared between scenarios when peer selection strategy uses informed decision and that does not use informed decision. The performance of the proposed approach is evaluated through the graph analysis which demonstrates that the inclusion of informed decision reduces the information dissemination delay remarkably.