A Green Computing Supportive Allocation Scheme Utilizing Genetic Algorithm and Support Vector Machine

Abstract

When a Physical Machine gets a job from user, it intends to complete it at any cost. Virtual Machine (VM) helps to attain maximum completion ratio. The Host to VM ratio increases with the increase in the workload over the system. The allocation policy of VM has ambiguities with leads to an overloaded Physical Machine (PM). This paper aims to reduce the overhead of the PMs. For the allocation, Modified Best Fit Decreasing (MBFD) algorithm is used to check the resources availability. For the allocation, Modified Best Fit Decreasing (MBFD) algorithm is used to check the resources availability. Genetic Algorithm (GA) has been used to optimize the MBFD performance by fitness function. For the cross-validation Polynomial Support Vector Machine (P-SVM) is used. It has been utilized for training and classification and accordingly, parameters, viz. (Service Level Agreement) SLA and Job Completion Ratio (JCR) are evaluated. A comparative analysis has been drawn in this article to depict the research work effectiveness and an improvement of 70% is perceived.

Review on the Interactions of Green Computing and Computational Intelligence techniques and their Applications to Real-World Problems

“…The adaptive neuro fuzzy clustering algorithm approach outperformed the existing best methods in the literature. In the paper by Ragmani et al [18] , a new green service for cloud computing based on fuzzy theoretical concepts is proposed. Cloud computing exhibits some key features such as elasticity and economy of scale that enable it to encounter many applications in the scientific, economic and industrial areas.…”