MOM-VMP: Multi-Objective Mayfly Optimization algorithm for VM Placement supported by Principal Component Analysis(PCA) in Cloud Data Center

Abstract

Abstract Virtual Machine Placement (VMP) is crucial in a cloud data cen-ter(CDC). It is a critical step carried out as part of the Virtual Machine (VM) placement to allocate the best Physical Machine (PM) to host the VMs. The efficacy of the virtual machine placement strategy has a considerable impact on cloud computing efficiency. The ineffec-tiveness of the VMP approach has a major negative impact on the CDC.Virtualization facilitated VM migration has met the ever-increasing demands of dynamic workload by transferring VMs inside CDC. Many resource management goals, including power efficiency, load balancing, fault tolerance, and system maintenance, are aided VM placement. As a result, VMP needs to assess characteristics that may impact placement performance and energy efficiency. Most past research has concentrated solely on reducing energy consumption while ignoring SLA (service level agreement) breaches, enhancing the resource usage of PMs, and ignoring the over-commitment issue. MOM-VMP To propose a multiobjective Mayfly VMP algorithm (MOM-VMP) meta-heuristic optimization algorithm with a massive CDC with different and multi-dimensional resources to handle these issues. A multi-objective dynamic VMP strategy is employed to reduce resource wastage, overcom-mitment ratio, migration time, SLA violation and energy consumption at the same time. This paper presents a dynamic multi-objective VMP in CDC based on overcommitment resource allocation to influence VM-PM mapping. We validated our method of conducting a performance evaluation study using the CloudSim tool. The experimental findings show that the suggested study decreases energy consumption, makespan, SLA violations, and PM overloading while enhancing resource utilization.