Elham Manoochehri - Computer Engineering Depatment, Azad University of Kermanshah, Kermanshah.Iran
Mahmood Ahamadi - Computer Engineering Department, Razi University of Kermanshah, Kermanshah.Iran

Using of Cloud computing services has been increased with the advancement of technology. Many companieshave started delivery their service using Cloud technology. One of the problems in this area is the high costs ofCloud servers. Apart from hardware costs another issue is the power consumption in these servers and high energycosts for companies. So finding some method to reduce energy consumption can save a lot of money every year.In this paper we propose a method for reducing energy consumption in cloud data centers. This method is basedon increasing execution speed of real time task in virtual machines to meet a certain threshold. This operation canreduce energy consumption by reducing negative impact of static power in data centers. Moreover systemresources can be released faster and system can accept more new tasks by faster execution of real time tasks. Wecompare our method with DVFS1 algorithm that in this algorithm each task ends at its given deadline. We useCloudSim toolkit for evaluating and comparing our method with DVFS. The result shows our method not onlyreduces energy consumption also increase the acceptance rate of jobs and reduce the return time of jobs.

Cloud computing, Tasks scheduling, Real-time tasks, Energy-efficient computing, DVFS, Optimalutilization level