A Flexible Dynamic Migration Strategy for Cloud Data Replica
Tian Bing, Wentao Yan, Yan Li, Chengyuan Wang, Fanfan Liu, Yaoting Tang, Shengya Han · 2017
In order to decrease the power corporation's data center construction and maintenance costs, a better solution is used by cloud computing data center. By using cloud computing data centers, power corporations can store geographically distributed users' data to meet the lower cost to meet the user's latency requirements. This electronic document is a "live" template and yet defines the components of your paper [title, text, heads, etc.] in its style sheet. This paper proposes a dynamic adaptive migration strategy for data replicas in cloud environment. Based on the workload based cloud computing, a dynamic scheduling mechanism is proposed to achieve a higher scalability, and increase the fault tolerance, and improve the ability to respond to changes in workload. The mechanism adjusts the number of replicas by changing the number of transaction requests monitored by the workload processor. By monitoring the workload to determine significant changes, a small step to repartition, and ultimately we achieve the purpose of maintaining a good overall partition. Through the dynamic data copy migration strategy, the dynamic data exchange between data nodes is completed. The experimental results show that the proposed method can significantly reduce the frequency of distributed transactions when the workload changes.