Study of Task Scheduling Algorithms for Energy Minimization in a Cloud Computing Environment

Abstract

Real-time applications are supported and permitted to run on virtualized resources that can be dynamically provisioned in a cloud computing environment. It is one of the effective platform services that enable a wide range of cloud infrastructure-based applications. With the aid of workflow systems, the construction of current scientific applications may now be completed in an uncomplicated and time-efficient approach. Implementing efficient workflow scheduling algorithms makes it feasible to increase utilization of resources, hence improving the performance of cloud computing and meeting user expectations. In cloud computing, the scheduling of jobs can directly affect the total amount of resources utilized and the operational expense of a system.. In this study, we have studied and discussed advantages and disadvantages of the various existing task scheduling methods employed by cloud service providers, such as Particle swarm optimization (PSO), Crow search algorithm (CSA), and Sparrow search algorithm (SSA). Several variables, including reaction time, load balance, execution time, and makespan, are examined to determine the best effective strategy for task scheduling under any conditions. Based on our research, we have concluded that CSA, CPO, and SSA are the most effective algorithms for reducing energy consumption, boosting performance, and shortening makespan.