DEWE: a framework for distributed elastic scientific workflow execution

Luke M. Leslie, Chiaki Sato, Young Choon Lee, Qingye Jiang, Albert Y. Zomaya

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

4 Citations (Scopus)

Abstract

As cloud computing is increasingly adopted, the open, on-demand nature of public clouds makes explicit consideration of the underlying environment highly advantageous in terms of decreasing cost and increasing elasticity. In this paper, we address the exploitation of such cloud capabilities and present DEWE, a framework for the distributed, elastic execution of scientific workflows. DEWE is designed to be easily extensible and customizable, and to provide a simple interface to automate deployment and elasticity in public clouds. Using Montage, an astronomical image mosaic engine, as a case study, and Amazon Web Services (AWS) as the cloud environment, we demonstrate the benefits DEWE can provide to scientists seeking to design job scheduling, data management, and resource allocation strategies with potentially unlimited on-demand resources at hand. Further, DEWE's visualization tool much leverages the analysis and evaluation of those strategies.

Original languageEnglish
Title of host publicationProceedings of the 13th Australasian Symposium on Parallel and Distributed Computing, AusPDC 2015
Place of PublicationSydney
PublisherAustralian Computer Society
Pages3-10
Number of pages8
Volume163
ISBN (Print)9781921770456
Publication statusPublished - 2015
Externally publishedYes
EventProceedings of the 13th Australasian Symposium on Parallel and Distributed Computing, AusPDC 2015 - Sydney, Australia
Duration: 27 Jan 201530 Jan 2015

Other

OtherProceedings of the 13th Australasian Symposium on Parallel and Distributed Computing, AusPDC 2015
CountryAustralia
CitySydney
Period27/01/1530/01/15

Fingerprint

Dive into the research topics of 'DEWE: a framework for distributed elastic scientific workflow execution'. Together they form a unique fingerprint.

Cite this