Task scheduling to reduce energy consumption and makespan of cloud computing using NSGA-II

Abstract

Abstract Cloud service usage has significantly increased due to ease in access, improved performance, and low acquisition costs. All the cloud users plan to get their jobs done quickly. Still, cloud providers are looking for ways to reduce energy costs, one of the highest prices in a cloud service environment. This is achieved by reducing the number of machines used to get the users job done. Consecutively, the makespan on the active machines increases, which often leads to customer dissatisfaction. This article proposes a multi-objective optimization model to minimize energy consumption and makespan for efficient task scheduling. This article additionally offers a Non-dominated Sorting Genetic Algorithm (NSGA) based algorithm to solve the optimization multi-objective task allocation problem. The performance of the proposed model and algorithms has been analyzed over various comprehensive experiments. The experimental results analysis highlights that the proposed model and algorithm reduces the makespan and energy consumption significantly compared to other traditional algorithms.