Proceedings of the 2008 ACM Symposium on Applied Computing 2008
DOI: 10.1145/1363686.1364181
|View full text |Cite
|
Sign up to set email alerts
|

Scheduling grid tasks under uncertain demands

Abstract: The uncertainty of the demands of grid applications can cause unpredicted performance and, consequently, can make ineffective schedules derived for target demand values. To produce effective results, schedulers need to take into account the difficulty in estimating the demands of applications. In this paper, a scheduler based on fuzzy optimization is proposed to deal with such uncertainties. It is shown, via numerical results, that the proposed scheduler presents advantages when compared to classical scheduler… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
2
0
1

Year Published

2009
2009
2018
2018

Publication Types

Select...
4
2
1

Relationship

0
7

Authors

Journals

citations
Cited by 7 publications
(3 citation statements)
references
References 11 publications
0
2
0
1
Order By: Relevance
“…For example, the uncertainties of application demands arise from the lack of precision in estimating the computation requirements for task executions and the amount of data to be transferred between these tasks. In these cases, a DAG may not be properly modelled by the users to faithfully represent the workflow application [14,16,18]. Another example is the uncertainties of available bandwidth in inter-cloud and intra-cloud links.…”
Section: Impact Of Using Imprecise Bandwidth Information On Workflow ...mentioning
confidence: 99%
See 1 more Smart Citation
“…For example, the uncertainties of application demands arise from the lack of precision in estimating the computation requirements for task executions and the amount of data to be transferred between these tasks. In these cases, a DAG may not be properly modelled by the users to faithfully represent the workflow application [14,16,18]. Another example is the uncertainties of available bandwidth in inter-cloud and intra-cloud links.…”
Section: Impact Of Using Imprecise Bandwidth Information On Workflow ...mentioning
confidence: 99%
“…The information about resource performance can be obtained from its hardware characteristics as well as from benchmarks [82,91,92,108,116,[121][122][123]137]. An important aspect of both sets is that they are prone to inaccuracy, introducing uncertainty issues to the scheduling process [14,16,18,19,24,30,31,46,68]. As we pointed out in Section 3.3.2, the bandwidth measurements are mostly given in large ranges rather than smaller ranges or even as deterministic values.…”
Section: Handling the Available Bandwidth Given In Ranges When Using ...mentioning
confidence: 99%
“…Enquanto a heterogeneidade implica complexidade na seleção de recursos para execução das tarefas, o comportamento dinâmico (variação no desempenho e disponibilidade dos recursos) implica em complexidade tanto na predição de desempenho quanto no reescalonamento. Escalonamento, predição de desempenho e reescalonamento têm recebido atenção substancial de pesquisadores em grades atualmente [7,29,77,92,52,53,104].…”
Section: Introductionunclassified