Enhanced Multi Objective Based Virtual Machine Optimization for Demand Management in Cloud Environment

Abstract

ABSTRACT newlineCloud computing enables the use of virtual machine resources and reduces operating cost. Whereas the selection of virtual machine still remains a challenge due to no proper resource utilization and lack of optimal resource allocation. The services and storage space required for a particular resource is specified by the user. Hence the significant challenge exists in cloud computing is the variant level of performance in concern to utilization, throughput, stability, etc. The proposed research quotEnhanced Multi-objective-based Virtual Machine Optimization For Demand Management in Cloud Environmentquot consists of three phases: i) Classification Phase, ii) Scheduling Phase, and iii) Optimization Phase. The first phase, quotEfficient User Classification Framework for Multi-objective-based Virtual Machines,quot efficiently handles multiple user requests by classifying them into valid and invalid categories. The second phase of the proposed research work Enhanced Multi-objective-based Virtual Machine Optimization For Demand Management in Cloud Environment. BCCOA is proposed for dynamic resource allocation in this venture. Based on this, it proves that the execution cost and respone time of the proposed method is low. Finally, the third phase Enhanced Optimization For Multi-Objective-Based Virtual Machine Model In Cloud monitors and optimizes the cloud resource allocation, enhancing the efficiency of the cloud environment. The framework utilizes the novel Optimized Mayfly Tanhoptimization- Virtual Machine Scheduling Algorithm. The average memory utilization (0.84) and average CPU utilization (0.93) are better than the other two existing approaches FCFS and SLPSO. Thus improving the cloud efficiency by dynamically adjusting VM scheduling showing exceptionally high utilization newline