Comparative Analysis for Task Scheduling Algorithms on Cloud Computing

Abstract

Recently, there has been a significant growth in the popularity of cloud computing systems as an on-demand computing service with a utility computing model with which the users pay as per the usage. One of the main goals of cloud computing is to provide efficient access to resources remotely while obtaining a maximum profit. Therefore, the principal issue in building cloud computing systems is the scheduling where it concentrates on assigning tasks to the available resources at a particular time. In this paper, we provided a comparative simulation study considering the most popular and common task scheduling algorithms in cloud computing, namely FCFS, STF, LTF, and RR algorithms. The evaluation was conducted by CloudSim considering both scheduling allocation policies which are time-shared and space-shared. The Simulation results showed that with space-shared allocation policy the STF algorithm outperformed the others in terms of the total completion time. On the other hand, time-shared allocation policy has a better performance in reducing the completion time of tasks compared to the space-shared policy.