R&D: Dynamic Convergent Replica Selection Strategy Based on Cloud Storage

IEEE Xplore has published, in 2019 International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM) proceesdings, an article written by Pu Zhao, China North Vehicle Research Institute, Xin Sun, Beijing Institute of Technology, Jingtao Shang, Jianjun Lin, Mingming Dong, and Bo Li, China North Vehicle Research Institute.

Abstract: “Replica selection strategy have been used in Cloud Storage to reduce data access latency, eliminate bottlenecks of hot spots and achieve load balance. This paper studies the replica selection strategy and replication strategy. By concerning real-time bandwidth, performance of the peer, and replica’s history request, following the principle that high valued replica has high proportionality to be select, a proportional matching based self-convergent replica selection strategy (PMC) based on HDFS (Hadoop Distributed File System) cloud storage environment is presented. The strategy has global optimization, effectively reduces access delay, balances load, eliminates hot bottlenecks. The simulation results show that the optimal selection strategy offers better performance by shortening the response time of replica selection.“