A Novel Technique for Accelerating Live Migration in Cloud Computing

摘要

Currently, cloud computing is being used in many scientific areas like geoscience, DNA sequencing, healthcare, and many more. In a cloud computing environment, a Virtual Machine (VM) is a virtualized instance of any computer that can execute almost all the tasks of a computer. VM migration can be referred to as a task to move VMs from one physical machine to another physical machine. During VM migration, there are many issues, such as fault occurrence, seamless connectivity, and maintaining the quality of service. The cloud service provider has to anticipate the server downtime and various other delays like slow processing of user’s request due to the occurrence of a fault, improper allocation of VMs, and many more. A reliable and advanced live migration optimization technique has been proposed in this work for a trustworthy cloud computing environment. There are three main algorithms in the proposed scheme considering the total migration time, namely Host Selection Migration Time (HSMT), VM Reallocation Migration Time (VMRMT), and VM Reallocation Bandwidth Usage (VMRBU). These algorithms support to enhance the performance of cloud computing environments by minimizing the migration time. The proposed scheme has been compared to some existing approaches, namely Kernel-based Virtual Machines (KVM) and Pareto Optimized Framework for Seamless VM Live Migration (POF-SVLM), to evaluate its performance. The results show that the proposed scheme reduces the total cores of CPU by 60-70%, downtime by 70-80%, data transfer rate by 40-50%, and migration time by 40-50%.