A data replica placement scheme for cloud storage under healthcare IoT environment

Massive medical and health care data has been generated, asking for research and development of cloud storage system. In order to improve its scalability and reliability at the same time shorten user access time, the multiple data replica scheme should be adopted and the proper location for each replica should be determined. In this paper, a multiple data replica placement scheme for cloud storage under health-care IoT environment is proposed. It based on p-median model with minimizing the total access cost, which includes user access cost and maintenance cost, as its optimization objective. It uses MOX (Mosquitoes Oviposition Mating) algorithm to find the optimal data replica placement solution and uses SA(Simulated Annealing) algorithm to optimize user access request assignment to the specific data replica. We have implemented the proposed scheme based on CloudSim and have done performance evaluation. Simulation results have shown that it can not only improve user access time and promote load balance but also enhance system scalability and reliability.