A resource scheduling model supporting differentiated service for grid computing

  • Weiyi Qi*
  • , Junwei Wu
  • , Minglu Li
  • , Chuliang Weng
  • *Corresponding author for this work

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

Abstract

To enable service level subscription in computing grid, the economic concept of differentiated marketing is introduced into grid resource scheduling and a novel resource-scheduling model, Differentiated Service Model (DSM), is presented. DSM uses the Strictness Factor, Greediness Factor and Credit Score to describe the characteristics of the users and resources, like service requirement and service level. A series of related strategies, including resource evaluating, job risk exposure rating, operation adjustment etc., have been developed to conduct the market players' behavior. A simulation examined DSM's performance and showed its effectiveness: With its aggregate job delivery punctuality being approximate to that of the conventional resource scheduling model, DSM delivered services to users with different quality corresponding to the subscribed service level, especially under a heavy system workload; DSM also balanced the benefit distribution among resources, avoiding the situation that some particular resources monopolize the market share.

Original languageEnglish
Title of host publicationProceedings of the 3rd ChinaGrid Annual Conference, ChinaGrid 2008
Pages47-54
Number of pages8
DOIs
StatePublished - 2008
Externally publishedYes
Event3rd ChinaGrid Annual Conference, ChinaGrid 2008 - Dunhuang, Gansu, China
Duration: 20 Aug 200822 Aug 2008

Publication series

NameProceedings of the 3rd ChinaGrid Annual Conference, ChinaGrid 2008

Conference

Conference3rd ChinaGrid Annual Conference, ChinaGrid 2008
Country/TerritoryChina
CityDunhuang, Gansu
Period20/08/0822/08/08

Fingerprint

Dive into the research topics of 'A resource scheduling model supporting differentiated service for grid computing'. Together they form a unique fingerprint.

Cite this