An Improved Dynamic Fault Tolerant Management Algorithm during VM migration in Cloud Data Center

Abstract

Abstract Virtualization technology is widely accomplished in the data centers of the Cloud, for computing resources. The computation of the data for corresponding users creates via a group of connected Virtual Machines (VM) in an accessible and flexible manner. It improves the utilization of resources and thus it minimizes the usage of more hardware. The VM based infrastructure overhaul schemes are necessary to repossess affected services in an appropriate manner. Dedicated routing clarifications are also desirable for the improvement of providing reliability of Virtual DC (Domain Controller) services. In the occasion of node failure, the corresponding virtual machine face the challenges in determining which and how many VMs should be selected for migration to maintain reliability. The selection of VM plays an important part in limiting the number of VM migrations. The problem consists of selecting one or more potential VMs for migration to reduce the resource load of the considered servers. We propose a new Dynamic Fault Tolerant VM Migration (DFTM) for the enforcement of cloud data center infrastructure reliability through advanced recovery mechanism of VN (Virtual Network) demands. Integer Linear Programming model is implemented for analyzing the route traffic which considers all related numerical factors to choose optimal VM via the optimal path. Then, Alternative Switch Identification Algorithm determines the new VM migration and routing is accomplished. We used Cloudsim to implement and measure the effectiveness of the proposed DFTM algorithm. Then, we compared our results with existing methodologies in terms of overall execution time, average resource usage time, disk usage, and other performance metrics. Experimental results illustrate that the proposed fault recovery algorithm enhances the survivability of the VM based cloud data center.