RGS-PBFT: A Reputation-Based Grouping and Supervision PBFT

Abstract

To address the problems of high communication overhead, insufficient robustness in master node election, and difficulty in timely management of faulty nodes in large-scale networks, the traditional PBFT consensus algorithm is proposed as a reputation-based grouping and supervision PBFT (RGS-PBFT). This method constructs a dynamic reputation score model based on the behavioral characteristics of nodes during the consensus process, such as verification correctness, voting participation, and operational stability. Based on this model, nodes are divided into consensus groups, candidate node groups, and ordinary node groups, enabling adaptive adjustment of node roles. During the master node election phase, the top 5% of nodes with the highest reputation scores from the consensus groups are selected as the candidate set. The ordinary node group and the candidate node group elect the master node through reputation-weighted voting, thus balancing the reliability of the master node with the decentralized nature of the election process. During the consensus process, only the consensus group participates in the core voting and confirmation process of PBFT to reduce communication complexity, while the remaining nodes mainly undertake verification and supervision responsibilities. Simultaneously, a monitoring and punishment mechanism for low-reputation nodes is introduced to limit, downgrade, and isolate faulty and abnormal nodes. Experimental results show that this mechanism, while maintaining Byzantine fault tolerance, can effectively reduce consensus communication overhead and improve master node election stability and overall system performance.