Multiple Correlation Cofficient Approch for VM Migration

Abstract

Cloud computing represents a major step up in computing whereby shared computation resources are provided on demand. In such a scenario, applications and data therefore, can be hosted by various virtual machines (VMs). Therefore, placement of virtual machines which host an application and migration of these virtual machines while the unexpected network latency or congestion occurs is critical to achieve and maintain the application performance. To address these issues, new VM migration approach is proposed which is an extension of the maximum correlation analysis. The previous approach was working on Maximum Correlation strategy to find which VMs have some high association based on only single criteria. However, such consolidation cannot trivial in sense that migration of VM can be based on only two factors, as it can result in violations of the SLA negotiated with customers and other current factors that playing role that time in degrading the current performance of the datacenter. Therefore, multiple maximum correlation approach is proposed which will be able to select faster based on the correlation of multiple factors. The correlation matrix is used which is based on multiple factors for efficient dynamic consolidation and migration of VMs due to some adversity or over utilization of resources. To maximize their reliability of their datacenters the Cloud providers have to apply VM migration policy.