Reputation-Based Miner Node Selection in Blockchain-Based Vehicular Edge Computing

Abstract

Vehicular edge computing (VEC) is one of the most efficient ways to have high functionality in resource-constrained connected vehicles. As the edge nodes in VEC holds paramount importance and highly sensitive data, we need to make sure the information exchange remains tamper-free. Although blockchain provides immutable and verifiable data storage solutions, the nodes that enable blockchain might be under attack such as a denial of service from various malicious actors. One way to nullify these types of attacks is to find the nodes under attack and remove them from the blockchain consensus process to ensure the proper functioning of the system, i.e., miner node selection. Similarly, in order to provide the decision on which node is to be removed from the network, we need a smart decision-making technique such as an artificial neural network (ANN). The ANN is used to calculate the reputation of the miner nodes. In this article, we propose a reputation-based miner node selection (RbMNS) in blockchain-based vehicular edge computing (BloVEC). We have used ANN and hyperledger fabric (HF) to implement the RbMNS and blockchain model in the system. We obtained the average transactional latency of 128 ms/109 ms with/without our implementation, respectively.