You are not logged in.

An epidemic model based temporal violation prediction strategy for large batch of parallel business cloud workflows

Luo, Haoyu, Liu, Jin, Liu, Xiao and Wang, Futian 2015, An epidemic model based temporal violation prediction strategy for large batch of parallel business cloud workflows, in DSDIS 2015: Proceedings of the IEEE Data Science and Data Intensive Systems 2015 International Conference, IEEE, Piscataway, N.J., pp. 182-189, doi: 10.1109/DSDIS.2015.16.

Attached Files
Name Description MIMEType Size Downloads

Title An epidemic model based temporal violation prediction strategy for large batch of parallel business cloud workflows
Author(s) Luo, Haoyu
Liu, Jin
Liu, Xiao
Wang, Futian
Conference name IEEE Data Science and Data Intensive Systems. International Conference (2015 : Sydney, NSW)
Conference location Sydney, NSW
Conference dates 11-13 Dec. 2015
Title of proceedings DSDIS 2015: Proceedings of the IEEE Data Science and Data Intensive Systems 2015 International Conference
Editor(s) Chen, Jinjun
Yang, Laurence T.
Publication date 2015
Conference series IEEE Data Science and Data Intensive Systems International Conference
Start page 182
End page 189
Total pages 8
Publisher IEEE
Place of publication Piscataway, N.J.
Keyword(s) temporal violations
parallel business workflow
cloud computing
queuing system
epidemic model
Summary Temporal violations often take place during the running of large batch of parallel business cloud workflow, which have a serious impact on the on-time completion of massive concurrent user requests. Existing studies have shown that local temporal violations (namely the delays of workflow activities) occurring during cloud workflow execution are the fundamental causes for failed on-time completion. Therefore, accurate prediction of temporal violations is a very important yet challenging task for business cloud workflows. In this paper, based on an epidemic model, a novel temporal violation prediction strategy is proposed to estimate the number of local temporal violations and the number of violations that must be handled so as to achieve a certain on-time completion rate before the execution of workflows. The prediction result can be served as an important reference for temporal violation prevention and handling strategies such as static resource reservation and dynamic provision. Specifically, we first analyze the queuing process of the parallel workflow activities, then we predict the number of potential temporal violations based on a novel temporal violation transmission model inspired by an epidemic model. Comprehensive experimental results demonstrate that our strategy can achieve very high prediction accuracy under different situations.
ISBN 9781509002146
Language eng
DOI 10.1109/DSDIS.2015.16
Field of Research 080503 Networking and Communications
Socio Economic Objective 970108 Expanding Knowledge in the Information and Computing Sciences
HERDC Research category E1 Full written paper - refereed
ERA Research output type E Conference publication
Copyright notice ©2015, IEEE
Persistent URL http://hdl.handle.net/10536/DRO/DU:30084564

Document type: Conference Paper
Collection: School of Information Technology
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 0 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 57 Abstract Views, 2 File Downloads  -  Detailed Statistics
Created: Thu, 30 Jun 2016, 18:16:18 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.