UPM Institutional Repository

A new method for scheduling divisible data on a heterogeneous two-levels hierarchical system


Citation

Shokripour, Amin and Othman, Mohamed and Ibrahim, Hamidah and Subramaniam, Shamala (2011) A new method for scheduling divisible data on a heterogeneous two-levels hierarchical system. Procedia Computer Science, 4. pp. 2196-2205. ISSN 1877-0509

Abstract

During the last decade, the use of parallel and distributed systems has become more common. In these systems, a huge chunk of data or computation is distributed among many systems in order to obtain better performance. Dividing data is one of the challenges in this type of systems. Divisible Load Theory (DLT) is proposed method for scheduling data distribution in parallel or distributed systems. In many researches carried out in this field, it was assumed that the used network topology is linear or one-level tree but that is not always true in real systems. In the large scale networks, hierarchical topology is usually used. In this article, we propose a new method which includes a closedform formula to schedule jobs in a heterogeneous distributed computing system in which its network topology is two-levels hierarchical system. The experiments show the calculated size for each processor is the best.


Download File

[img] PDF
A New Method for Scheduling Divisible Data on a Heterogeneous Two-Levels Hierarchical System.pdf
Restricted to Repository staff only

Download (373kB)

Additional Metadata

Item Type: Article
Divisions: Faculty of Computer Science and Information Technology
DOI Number: https://doi.org/10.1016/j.procs.2011.04.240
Publisher: Elsevier
Keywords: Divisible load theory; Scheduling; Unreliable systems; Heterogeneous; Dedicated systems
Depositing User: Mohd Noor Ismail
Date Deposited: 03 May 2016 09:28
Last Modified: 03 May 2016 09:28
Altmetrics: http://www.altmetric.com/details.php?domain=psasir.upm.edu.my&doi=10.1016/j.procs.2011.04.240834
URI: http://psasir.upm.edu.my/id/eprint/42916
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item