Cloud provisioning in the QED regime

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

1 Citation (Scopus)
3 Downloads (Pure)

Abstract

We design a dynamic algorithm for dimensioning and stabilizing a cloud provisioning process. We model the process as a semi-open tandem network consisting of a multi-server queue with host servers that respond to new requests of cloud users and an infinite-server queue that contains the active cloud users. The algorithm matches load predictions by jointly setting the number of host servers and the total available capacity. This dual setting is time-dependent and based on the modified offered load (MOL) method. The algorithm is made to perform in the Quality-and-Efficiency-Driven (QED) regime to achieve economies of scale, and is equipped with the feature of repeated requests, which lets initially blocked users retry to get access to the cloud system after a certain delay. Extensive numerical simulations show that the algorithm stabilizes performance at high QoS-levels, even in face of strongly time-varying loads and repeated requests.
Original languageEnglish
Title of host publicationVALUETOOLS'15 Proceedings of the 9th EAI International Conference on Performance Evaluation Methodologies and Tools, 14-16 December 2015, Berlin, Germany
Place of PublicationNew York
PublisherAssociation for Computing Machinery, Inc
Pages180-187
ISBN (Print)978-1-63190-096-9
DOIs
Publication statusPublished - 2016

Fingerprint

Servers
Quality of service
Computer simulation

Cite this

Sloothaak, F., van Leeuwaarden, J. S. H., & Mathijsen, B. W. J. (2016). Cloud provisioning in the QED regime. In VALUETOOLS'15 Proceedings of the 9th EAI International Conference on Performance Evaluation Methodologies and Tools, 14-16 December 2015, Berlin, Germany (pp. 180-187). New York: Association for Computing Machinery, Inc. https://doi.org/10.4108/eai.14-12-2015.2262649
Sloothaak, F. ; van Leeuwaarden, J.S.H. ; Mathijsen, B.W.J. / Cloud provisioning in the QED regime. VALUETOOLS'15 Proceedings of the 9th EAI International Conference on Performance Evaluation Methodologies and Tools, 14-16 December 2015, Berlin, Germany. New York : Association for Computing Machinery, Inc, 2016. pp. 180-187
@inproceedings{d17051c11fc6460f849d1827399c27d3,
title = "Cloud provisioning in the QED regime",
abstract = "We design a dynamic algorithm for dimensioning and stabilizing a cloud provisioning process. We model the process as a semi-open tandem network consisting of a multi-server queue with host servers that respond to new requests of cloud users and an infinite-server queue that contains the active cloud users. The algorithm matches load predictions by jointly setting the number of host servers and the total available capacity. This dual setting is time-dependent and based on the modified offered load (MOL) method. The algorithm is made to perform in the Quality-and-Efficiency-Driven (QED) regime to achieve economies of scale, and is equipped with the feature of repeated requests, which lets initially blocked users retry to get access to the cloud system after a certain delay. Extensive numerical simulations show that the algorithm stabilizes performance at high QoS-levels, even in face of strongly time-varying loads and repeated requests.",
author = "F. Sloothaak and {van Leeuwaarden}, J.S.H. and B.W.J. Mathijsen",
year = "2016",
doi = "10.4108/eai.14-12-2015.2262649",
language = "English",
isbn = "978-1-63190-096-9",
pages = "180--187",
booktitle = "VALUETOOLS'15 Proceedings of the 9th EAI International Conference on Performance Evaluation Methodologies and Tools, 14-16 December 2015, Berlin, Germany",
publisher = "Association for Computing Machinery, Inc",
address = "United States",

}

Sloothaak, F, van Leeuwaarden, JSH & Mathijsen, BWJ 2016, Cloud provisioning in the QED regime. in VALUETOOLS'15 Proceedings of the 9th EAI International Conference on Performance Evaluation Methodologies and Tools, 14-16 December 2015, Berlin, Germany. Association for Computing Machinery, Inc, New York, pp. 180-187. https://doi.org/10.4108/eai.14-12-2015.2262649

Cloud provisioning in the QED regime. / Sloothaak, F.; van Leeuwaarden, J.S.H.; Mathijsen, B.W.J.

VALUETOOLS'15 Proceedings of the 9th EAI International Conference on Performance Evaluation Methodologies and Tools, 14-16 December 2015, Berlin, Germany. New York : Association for Computing Machinery, Inc, 2016. p. 180-187.

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

TY - GEN

T1 - Cloud provisioning in the QED regime

AU - Sloothaak, F.

AU - van Leeuwaarden, J.S.H.

AU - Mathijsen, B.W.J.

PY - 2016

Y1 - 2016

N2 - We design a dynamic algorithm for dimensioning and stabilizing a cloud provisioning process. We model the process as a semi-open tandem network consisting of a multi-server queue with host servers that respond to new requests of cloud users and an infinite-server queue that contains the active cloud users. The algorithm matches load predictions by jointly setting the number of host servers and the total available capacity. This dual setting is time-dependent and based on the modified offered load (MOL) method. The algorithm is made to perform in the Quality-and-Efficiency-Driven (QED) regime to achieve economies of scale, and is equipped with the feature of repeated requests, which lets initially blocked users retry to get access to the cloud system after a certain delay. Extensive numerical simulations show that the algorithm stabilizes performance at high QoS-levels, even in face of strongly time-varying loads and repeated requests.

AB - We design a dynamic algorithm for dimensioning and stabilizing a cloud provisioning process. We model the process as a semi-open tandem network consisting of a multi-server queue with host servers that respond to new requests of cloud users and an infinite-server queue that contains the active cloud users. The algorithm matches load predictions by jointly setting the number of host servers and the total available capacity. This dual setting is time-dependent and based on the modified offered load (MOL) method. The algorithm is made to perform in the Quality-and-Efficiency-Driven (QED) regime to achieve economies of scale, and is equipped with the feature of repeated requests, which lets initially blocked users retry to get access to the cloud system after a certain delay. Extensive numerical simulations show that the algorithm stabilizes performance at high QoS-levels, even in face of strongly time-varying loads and repeated requests.

U2 - 10.4108/eai.14-12-2015.2262649

DO - 10.4108/eai.14-12-2015.2262649

M3 - Conference contribution

SN - 978-1-63190-096-9

SP - 180

EP - 187

BT - VALUETOOLS'15 Proceedings of the 9th EAI International Conference on Performance Evaluation Methodologies and Tools, 14-16 December 2015, Berlin, Germany

PB - Association for Computing Machinery, Inc

CY - New York

ER -

Sloothaak F, van Leeuwaarden JSH, Mathijsen BWJ. Cloud provisioning in the QED regime. In VALUETOOLS'15 Proceedings of the 9th EAI International Conference on Performance Evaluation Methodologies and Tools, 14-16 December 2015, Berlin, Germany. New York: Association for Computing Machinery, Inc. 2016. p. 180-187 https://doi.org/10.4108/eai.14-12-2015.2262649