Balanced Hashgraph Based on Dynamic MCMC: Efficient, Practical and Compatible

In a blockchain system based on the HashGraph consensus algorithm, picking a target server for block propagation is a key step. The traditional HashGraph blockchain system uses a completely random approach to pick the target server, which has the advantage of ensuring the security of the system and reducing the impact of attacks and single server failures received by the system. However, the random selection of target servers may lead to a situation where low performance servers are under high load but high performance servers are under load. In order to make each server process the block data with maximum performance, this paper proposes a balanced up-linking strategy, which calculates the server's reputation by evaluating the status of four dimensions, such as remaining performance, security, response time, and trustworthiness of the server, and then constructs a geometric probability model by Markov model and Monte Carlo method, so that the block is randomly propagated to each server with a specific probability according to the server status. In the process of running the blockchain system with this strategy, the probability of propagation to each server is dynamically adjusted according to the changing server status, so that the frequency distribution of all servers in the cluster receiving blocks obeys the target probability distribution. We evaluate the performance of our approach through extensive simulations and experiments, and the results demonstrate the feasibility and effectiveness of the proposed approach.