A multi-parameter scheduling method of dynamic workloads for big data calculation in cloud computing.
Saved in:
| Title: | A multi-parameter scheduling method of dynamic workloads for big data calculation in cloud computing. |
|---|---|
| Authors: | Hanani, Ali1 ali.hanani@srbiau.ac.ir, Rahmani, Amir1 rahmani@srbiau.ac.ir, Sahafi, Amir2 sahafi@iau.ac.ir |
| Source: | Journal of Supercomputing. Nov2017, Vol. 73 Issue 11, p4796-4822. 27p. |
| Subjects: | Cloud computing, Workload of computers, Big data, Mathematical optimization, Algorithms |
| Abstract: | Workload scheduling in cloud computing is currently an active research field. Scheduling plays an important role in cloud computing performance, especially when the platform is used for big data analysis and as less predictable workloads dynamically enter the clouds. Finding the optimized scheduling solution with different parameters in different environments is still a challenging issue. In dynamic environments such as cloud, scheduling strategies should feature rapid altering to be able to adapt more easily to the changes in input workloads. However, achieving an optimized solution is an important issue, which has a trade-off with the speed of finding the solution. In this article, an ordinal optimization method is proposed that considers the volume of workloads, load balancing and the volume of exchanged messages among virtual clusters, considering the replications. The algorithm in the present paper is based on ordinal optimization (OO) and evolutionary OO. In any time periods, a criterion is calculated to determine the similarity of workloads in two-consequence time periods, which is appropriate for timely changes in the scheduling procedure. In this paper, considering more than one parameter, a proper scheduling would be created for each time period. This scheduler is an organization for the number of virtual machines for each virtual cluster, but if there is a desirable similarity between workloads of two-consequence time periods, this procedure would be ignored. The results show that a more optimized solution is obtained in comparison with the rated methods, such as blind pink, OO, Monte Carlo and eOO in a reasonable time. The suggested method is flexible and it is possible to change the weight ratio of the proposed criteria in different environments to be consistent with different environmental conditions. The results show that proposed method achieved up to 28% performance improvement in comparison with eOO. [ABSTRACT FROM AUTHOR] |
| Copyright of Journal of Supercomputing is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Links: – Type: pdflink Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 125744827 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: A multi-parameter scheduling method of dynamic workloads for big data calculation in cloud computing. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Hanani%2C+Ali%22">Hanani, Ali</searchLink><relatesTo>1</relatesTo><i> ali.hanani@srbiau.ac.ir</i><br /><searchLink fieldCode="AR" term="%22Rahmani%2C+Amir%22">Rahmani, Amir</searchLink><relatesTo>1</relatesTo><i> rahmani@srbiau.ac.ir</i><br /><searchLink fieldCode="AR" term="%22Sahafi%2C+Amir%22">Sahafi, Amir</searchLink><relatesTo>2</relatesTo><i> sahafi@iau.ac.ir</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Journal+of+Supercomputing%22">Journal of Supercomputing</searchLink>. Nov2017, Vol. 73 Issue 11, p4796-4822. 27p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Cloud+computing%22">Cloud computing</searchLink><br /><searchLink fieldCode="DE" term="%22Workload+of+computers%22">Workload of computers</searchLink><br /><searchLink fieldCode="DE" term="%22Big+data%22">Big data</searchLink><br /><searchLink fieldCode="DE" term="%22Mathematical+optimization%22">Mathematical optimization</searchLink><br /><searchLink fieldCode="DE" term="%22Algorithms%22">Algorithms</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Workload scheduling in cloud computing is currently an active research field. Scheduling plays an important role in cloud computing performance, especially when the platform is used for big data analysis and as less predictable workloads dynamically enter the clouds. Finding the optimized scheduling solution with different parameters in different environments is still a challenging issue. In dynamic environments such as cloud, scheduling strategies should feature rapid altering to be able to adapt more easily to the changes in input workloads. However, achieving an optimized solution is an important issue, which has a trade-off with the speed of finding the solution. In this article, an ordinal optimization method is proposed that considers the volume of workloads, load balancing and the volume of exchanged messages among virtual clusters, considering the replications. The algorithm in the present paper is based on ordinal optimization (OO) and evolutionary OO. In any time periods, a criterion is calculated to determine the similarity of workloads in two-consequence time periods, which is appropriate for timely changes in the scheduling procedure. In this paper, considering more than one parameter, a proper scheduling would be created for each time period. This scheduler is an organization for the number of virtual machines for each virtual cluster, but if there is a desirable similarity between workloads of two-consequence time periods, this procedure would be ignored. The results show that a more optimized solution is obtained in comparison with the rated methods, such as blind pink, OO, Monte Carlo and eOO in a reasonable time. The suggested method is flexible and it is possible to change the weight ratio of the proposed criteria in different environments to be consistent with different environmental conditions. The results show that proposed method achieved up to 28% performance improvement in comparison with eOO. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Journal of Supercomputing is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=125744827 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s11227-017-2050-6 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 27 StartPage: 4796 Subjects: – SubjectFull: Cloud computing Type: general – SubjectFull: Workload of computers Type: general – SubjectFull: Big data Type: general – SubjectFull: Mathematical optimization Type: general – SubjectFull: Algorithms Type: general Titles: – TitleFull: A multi-parameter scheduling method of dynamic workloads for big data calculation in cloud computing. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Hanani, Ali – PersonEntity: Name: NameFull: Rahmani, Amir – PersonEntity: Name: NameFull: Sahafi, Amir IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 11 Text: Nov2017 Type: published Y: 2017 Identifiers: – Type: issn-print Value: 09208542 Numbering: – Type: volume Value: 73 – Type: issue Value: 11 Titles: – TitleFull: Journal of Supercomputing Type: main |
| ResultId | 1 |
