Abstract: With the popularization and development of digital currency,the blockchain technology enters the public’s vision,and has been hailed as the fourth milestone in credit history,the cornerstone of future credit^[1].However,blockchain technology is also facing problems such as low efficiency of consensus and waste of computing power.The K-medoids clustering algorithm is used to cluster and hierarchically divide the large scale network nodes participating in the blockchain consensus based on features,and then the improved multi-centered PBFT (Practical Byzantine Fault Tole-rance) consensus algorithm is applied to the clustered model.Moreover,in order to improve the controllability of clustering algorithm to cluster nodes in blockchain model under various scenarios,this paper improved K-medoids algorithm.Simulation results show that when appropriate clustering features are selected to evaluate the similarity between nodes,the improved algorithm K-PBFT reduces the single-consensus time consumption by 20%,and the consensus process communication times can be reduced by three orders of magnitude.The experimental results show that K-PBFT optimizes the consensus process involving large-scale nodes,so that the blockchain technology can be applied to a wider range of application scenarios.

Key words: Blockchain, Clustering algorithm, K-medoids, Practical byzantine fault tolerance