An Intelligent and Dynamic Replication Scheme for Reliable Cloud Environment

Recently, cloud computing research, especially Virtual Machine based replication schemes and their applications, were becoming prevalent. A cloud data center (DC) comprises of hosts with an enormous of virtual machines (VMs) where determining replica quantity and replication order is a tedious task to minimize cost and bandwidth. Majority of the existing dynamic replication techniques rely on budget constraints and server failure rate to guarantee customer requirements. But, there is a strong need to determine replication order of servers to retain the performance and system stability. In this paper, we suggest two different algorithms for better selection with proper and intelligent placement of replicas in the cloud region. The proposed algorithms towards dynamic replication are request based replica selection (RRS) and ant colony optimization (ACO). The foremost proposed algorithm was request based replica selection used for obtaining the best selected replicas depends upon the VM performance ranking and failure probability based on the task requirement. Conversely, the subsequent offered algorithm is ACO that is helpful to find the best location to place the designated replica depends on the least-cost distance metric, and the replicas availability in order to encompass and regulate with the entire network load and the link bottlenecks. The performance of proposed techniques using CloudSim was evaluated against various pro-active fault tolerance strategies. The simulation results gives that dynamic replica selection provides efficient task replication when compared with the existing pro-active algorithms. Additionally, ACO realizes high availability, low cost, and less bandwidth utilization.