Abstract
Maintaining replicated data between nodes can improve the dependability of data. We propose a probabilistic trapezoid protocol for replicated data that combines the trapezoid protocol with the concept of a probabilistic quorum system. We analyzed the read availability, the latest version's read availability and the average number of nodes accessed for the protocol. Our numerical evaluations demonstrated that it improves not only the read availability but also the latest version's read availability. Furthermore, when the number of nodes is greater than 100, it could effectively reduce the system's load. We designed and implemented a file transfer protocol to replicate data. Experimental results proved that the trapezoid protocol could achieve a better throughput than the voting system or the grid protocol. Despite node failure, the probabilistic trapezoid protocol also achieved a relatively better throughput.
