Finding candidate spots for replica servers based on demand fluctuation

Masato Asahara, Akio Shimada, Hiroshi Yamada, Kenji Kono

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Many service providers distribute various kinds of content over the Internet. They often use replica servers to provide stable service. To position them appropriately, service providers must predict the demands for their services and provide computing capacity sufficient for servicing the demands. Unfortunately, predicting demands is difficult because demand for a service usually fluctuates. Our research group is developing ExaPeer, an infrastructure that apportions computing capacity to services running on hundreds or thousands of trusted machines all over the Internet. In this paper, we describe ExaPeer's approach to dynamically selecting candidate spots for replica servers. The runtime system in ExaPeer detects fluctuations in demand and then dynamically selects candidate spots on which replica servers should be placed to best meet the demand. Experimental results demonstrate that the candidate spots selected by ExaPeer work better than manually selected ones even if the scale of demand changes rapidly.

Original languageEnglish
Title of host publicationProceedings of the International Conference on Parallel and Distributed Systems - ICPADS
Volume1
DOIs
Publication statusPublished - 2007
Event13th International Conference on Parallel and Distributed Systems, ICPADS - Hsinchu, Taiwan, Province of China
Duration: 2007 Dec 52007 Dec 7

Other

Other13th International Conference on Parallel and Distributed Systems, ICPADS
CountryTaiwan, Province of China
CityHsinchu
Period07/12/507/12/7

Fingerprint

Servers
Internet

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Asahara, M., Shimada, A., Yamada, H., & Kono, K. (2007). Finding candidate spots for replica servers based on demand fluctuation. In Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS (Vol. 1). [4447737] https://doi.org/10.1109/ICPADS.2007.4447737

Finding candidate spots for replica servers based on demand fluctuation. / Asahara, Masato; Shimada, Akio; Yamada, Hiroshi; Kono, Kenji.

Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS. Vol. 1 2007. 4447737.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Asahara, M, Shimada, A, Yamada, H & Kono, K 2007, Finding candidate spots for replica servers based on demand fluctuation. in Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS. vol. 1, 4447737, 13th International Conference on Parallel and Distributed Systems, ICPADS, Hsinchu, Taiwan, Province of China, 07/12/5. https://doi.org/10.1109/ICPADS.2007.4447737
Asahara M, Shimada A, Yamada H, Kono K. Finding candidate spots for replica servers based on demand fluctuation. In Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS. Vol. 1. 2007. 4447737 https://doi.org/10.1109/ICPADS.2007.4447737
Asahara, Masato ; Shimada, Akio ; Yamada, Hiroshi ; Kono, Kenji. / Finding candidate spots for replica servers based on demand fluctuation. Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS. Vol. 1 2007.
@inproceedings{37cca7899df14e94b8ee5aaf6492230b,
title = "Finding candidate spots for replica servers based on demand fluctuation",
abstract = "Many service providers distribute various kinds of content over the Internet. They often use replica servers to provide stable service. To position them appropriately, service providers must predict the demands for their services and provide computing capacity sufficient for servicing the demands. Unfortunately, predicting demands is difficult because demand for a service usually fluctuates. Our research group is developing ExaPeer, an infrastructure that apportions computing capacity to services running on hundreds or thousands of trusted machines all over the Internet. In this paper, we describe ExaPeer's approach to dynamically selecting candidate spots for replica servers. The runtime system in ExaPeer detects fluctuations in demand and then dynamically selects candidate spots on which replica servers should be placed to best meet the demand. Experimental results demonstrate that the candidate spots selected by ExaPeer work better than manually selected ones even if the scale of demand changes rapidly.",
author = "Masato Asahara and Akio Shimada and Hiroshi Yamada and Kenji Kono",
year = "2007",
doi = "10.1109/ICPADS.2007.4447737",
language = "English",
isbn = "9781424418909",
volume = "1",
booktitle = "Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS",

}

TY - GEN

T1 - Finding candidate spots for replica servers based on demand fluctuation

AU - Asahara, Masato

AU - Shimada, Akio

AU - Yamada, Hiroshi

AU - Kono, Kenji

PY - 2007

Y1 - 2007

N2 - Many service providers distribute various kinds of content over the Internet. They often use replica servers to provide stable service. To position them appropriately, service providers must predict the demands for their services and provide computing capacity sufficient for servicing the demands. Unfortunately, predicting demands is difficult because demand for a service usually fluctuates. Our research group is developing ExaPeer, an infrastructure that apportions computing capacity to services running on hundreds or thousands of trusted machines all over the Internet. In this paper, we describe ExaPeer's approach to dynamically selecting candidate spots for replica servers. The runtime system in ExaPeer detects fluctuations in demand and then dynamically selects candidate spots on which replica servers should be placed to best meet the demand. Experimental results demonstrate that the candidate spots selected by ExaPeer work better than manually selected ones even if the scale of demand changes rapidly.

AB - Many service providers distribute various kinds of content over the Internet. They often use replica servers to provide stable service. To position them appropriately, service providers must predict the demands for their services and provide computing capacity sufficient for servicing the demands. Unfortunately, predicting demands is difficult because demand for a service usually fluctuates. Our research group is developing ExaPeer, an infrastructure that apportions computing capacity to services running on hundreds or thousands of trusted machines all over the Internet. In this paper, we describe ExaPeer's approach to dynamically selecting candidate spots for replica servers. The runtime system in ExaPeer detects fluctuations in demand and then dynamically selects candidate spots on which replica servers should be placed to best meet the demand. Experimental results demonstrate that the candidate spots selected by ExaPeer work better than manually selected ones even if the scale of demand changes rapidly.

UR - http://www.scopus.com/inward/record.url?scp=48049100570&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=48049100570&partnerID=8YFLogxK

U2 - 10.1109/ICPADS.2007.4447737

DO - 10.1109/ICPADS.2007.4447737

M3 - Conference contribution

AN - SCOPUS:48049100570

SN - 9781424418909

VL - 1

BT - Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS

ER -