Efficient vCPU Utilization for Reducing Energy Consumption in Cloud Data Centers

Abstract

As the demand for cloud computing services continues to grow, the requirement for expanding cloud data centers also increases. One main issue facing this growth is the huge amount of energy consumed by the cloud data centers. The massive energy consumption expenses considered the main problem for cloud service providers. Recent reports revealed that the electricity expenses of Information and communications technology or (ICT) devices occupy 42% per month of the total budgets. Nevertheless, the continuous increase in energy consumption has become the main challenging subject. Due to this reason, researches have proposed many techniques and approaches (such as virtual machine VM consolidation, Voltage and Frequency Scaling, VM migration policies, etc.) for addressing this issue. This paper presents a study to evaluate the influence of controlling virtual machine central process unit (vCPU) on energy consumption of Cloud data center. CloudSim simulator is used to apply the dynamic voltage and frequency scaling (DVFS) technique with the proposed approach while processing different types of general purpose cloud computing applications (video streaming, file compression process, and video games). Results indicate that about 13% of data center energy was saved compared with the base DVFS system. This saving percentage result was a better percentage comparing with other results obtained from previous work.