AI-Enabled Blockchain Consensus Node Selection in Cluster-Based Vehicular Networks

Abstract

In the scenario of highly mobile nodes, applying blockchain not only needs to ensure high performance and security but also needs to consider the low stability of consensus nodes. We introduce a novel framework to reduce the negative impact of low-stable consensus nodes. In addition, we have developed an intelligent algorithm for selecting the optimal number of Mobile Consensus Nodes (MCNs) considering various parameters including Stability of Node (SoN). The results demonstrate that the proposed scheme improves the average reputation and stability of consensus nodes by 6.8% and 17.5%, respectively while reducing the average message counts by 33.9%.