PROJECT TITLE :

An On-Line Virtual Machine Consolidation Strategy for Dual Improvement in Performance and Energy Conservation of Server Clusters in Cloud Data Centers

ABSTRACT:

Improving the energy efficiency of cloud computing has become a primary focus of research in recent years as a direct response to the massive amounts of power that are consumed by data centers. However, it is difficult to decrease energy consumption while keeping system performance stable and without increasing the risk of violating a Service Level Agreement. The majority of the existing consolidation strategies for virtual machines (VMs) take into account system performance and Quality of Service (QoS) metrics as constraints. This typically results in a large scheduling overhead and makes it impossible to achieve effective improvement in energy efficiency without making some sacrifices in system performance as well as the quality of cloud services. First, we will define the metrics of peak power efficiency and optimal utilization for a variety of different physical machines in this article (PMs). Then, we put forward the idea of Peak Efficiency Aware Scheduling, or PEAS for short, which is an innovative method for the placement and reallocation of virtual machines that aims to simultaneously achieve an improvement in performance and a reduction in energy consumption from the point of view of server clusters. On-the-fly virtual machine allocation and reallocation is handled by PEAS, and every effort is made to keep physical machines operating at their highest possible level of power efficiency by consolidating VMs. Extensive testing on Cloudsim demonstrates that PEAS outperforms a number of energy-aware consolidation algorithms in terms of energy consumption, system performance, and a variety of quality of service metrics.