Intelligent Randomize Round Robin for Cloud Computing

Intelligent Randomize Round Robin for Cloud Computing

Muneer O. Bani Yassein (Department of Computer Science, Jordan University of Science and Technology, Irbid, Jordan), Yaser M. Khamayseh (Department of Computer Science, Jordan University of Science and Technology, Irbid, Jordan) and Ali M. Hatamleh (Department of Computer Science, Jordan University of Science and Technology, Irbid, Jordan)
Copyright: © 2013 |Pages: 7
DOI: 10.4018/ijcac.2013010103
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Cloud computing is a recent scientific revolution in information technology, it is considered as the basic infrastructure of ubiquitous computing. It supports various features including, Internet based computing, and resources sharing. Delivery of services is provided to computers and other devices upon request. In other words, it is a technology based on the internet and central remote servers to maintain data and applications. This technology allows consumers and enterprises to use applications without the need of installing them or allowing access to their personal files at any computer with internet access. Among different users that may access the cloud data center, cloud computing must include job scheduling to organize and monitor these jobs, and to achieve fairness among all users. One of the most popular job scheduling algorithms is Round Robin (RR). This paper proposes an enhancement to the traditional RR, namely Randomized Round Robin (RRR). The enhanced version of RR algorithms is based on random selection for processes that come from different users to achieve near optimal selection of jobs to be served. A simulation has been carried out using CloudSim simulator V 3.0 to test the performance of the proposed scheme in terms of different evaluation metrics such as average throughput and average turnaround time.
Article Preview

Several algorithms have been proposed to address the problem of job scheduling in a distributed environment such as the cloud system; the following part discusses some of these algorithms:

Round Robin (RR)

RR Algorithm is a pre-emptive version of FCFS scheduling algorithm. Tasks from different users arrive at the server one after another, and then the scheduler serves the tasks based on their arrival time in a FCFS manner. The processor executes the task from the ready queue based on the predefined Time Slice (TS). If a task from a specific user is still running and needs more time to be fully served while TS ends, then the execution of the task is pre-empt and is added to the end of the ready queue. After that, the scheduler seizes the processor to the next task in the ready queue (Helmy, 2007; Linlin, Kumar, & Rajkumar, 2011; Song et al., 2008).

The pre-empted task is served during the next round of the scheduler. In each round, the scheduler serves each task for a fixed amount of time. The process of RR is shown in Figure 1.

Figure 1.

Round Robin Scheduler

Complete Article List

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