Energy Aware Grid Scheduling for Dependent Task Using Genetic Algorithm

Energy Aware Grid Scheduling for Dependent Task Using Genetic Algorithm

Shiv Prakash (School of Computer and Systems Sciences, Jawaharlal Nehru University, New Delhi, India) and Deo Prakash Vidyarthi (School of Computer and Systems Sciences, Jawaharlal Nehru University, New Delhi, India)
Copyright: © 2016 |Pages: 19
DOI: 10.4018/IJDST.2016040102
OnDemand PDF Download:
$37.50

Abstract

Consumption of energy in the large computing system is an important issue not only because energy sources are depleting fast but also due to the deteriorating environmental conditions. A computational grid is a large heterogeneous distributed computing platform which consumes enormous energy in the task execution. Energy-aware job scheduling, in the computational grid, is an important issue that has been addressed in this work. If the tasks are properly scheduled, keeping the optimal energy concern, it is possible to save the energy consumed by the system in the task execution. The prime objective, in this work, is to schedule the dependent tasks of a job, on the grid nodes with optimal energy consumption. Energy consumption is estimated with the help of Dynamic Voltage Frequency Scaling (DVFS). Makespan, while optimizing the energy consumption, is also taken care of in the proposed model. GA is applied for the purpose and therefore the model is named as Energy Aware Genetic Algorithm (EAGA). Performance evaluation of the proposed model is done using GridSim simulator. A comparative study with other existing models viz. min-min and max-min proves the efficacy of the proposed model.
Article Preview

Apart from makespan, energy, reliability, availability etc. of resources are some of the important Quality of Service (QoS) parameters (Ding, Luo, & Gao, 2010) often optimized by scheduling the tasks suitably on the CG nodes. The scheduling problem in grid computing has been extensively discussed in literature (Foster, & Kesselman, 2003; Berman, Fox, & Hey, 2003; Ding, Luo, & Gao, 2010; Prakash, & Vidyarthi, 2013; Parsa, & Entezari-Maleki, 2012; Chen, & Zhang, 2009; Aron, & Chana, 2012; Kashyap, & Vidyarthi, 2012; Kashyap, & Vidyarthi, 2013). As the problem is NP-Hard, Genetic algorithm (GA) is also often used to address this problem in grid computing (Foster, & Kesselman, 2003; Johnson, & Garey, 1979; Xhafa, & Abraham, 2008; Xhafa, & Abraham, 2010; Carretero, Xhafa, & Abraham, 2007; Chen, & Zhang, 2009; Kashyap, & Vidyarthi, 2012). Some of the recent related work of grid scheduling is as follows.

Complete Article List

Search this Journal:
Reset
Open Access Articles
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing