Queuing theory-based latency/Power tradeoff models for replicated search engines

Large-scale search engines are built upon huge infrastructures involvingthousands of computers in order to achieve fast response times. In contrast, the energy consumed (and hence the financial cost) is also high, leading to environmental damage. This paper proposes new approaches to increase energy...

ver descrição completa

Detalhes bibliográficos
Autores: Freire, Ana, Macdonald, Craig, Tonellotto, Nicola, Ounis, Iadh, Cacheda, Fidel
Formato: artículo
Estado:Versión publicada
Fecha de publicación:2015
País:España
Recursos:Universitat Pompeu Fabra
Repositorio:Repositorio Digital de la UPF
OAI Identifier:oai:repositori.upf.edu:10230/43870
Acesso em linha:http://hdl.handle.net/10230/43870
http://dx.doi.org/10.3217/jucs-021-13-1790
Access Level:acceso abierto
Palavra-chave:Green IR
Information retrieval
Power consumption
Queueing theory
Search engines
id ES_453af690a4ae10b4841ba6fcf42d14f3
oai_identifier_str oai:repositori.upf.edu:10230/43870
network_acronym_str ES
network_name_str España
repository_id_str
spelling Queuing theory-based latency/Power tradeoff models for replicated search enginesFreire, AnaMacdonald, CraigTonellotto, NicolaOunis, IadhCacheda, FidelGreen IRInformation retrievalPower consumptionQueueing theorySearch enginesLarge-scale search engines are built upon huge infrastructures involvingthousands of computers in order to achieve fast response times. In contrast, the energy consumed (and hence the financial cost) is also high, leading to environmental damage. This paper proposes new approaches to increase energy and financial savings in large-scale search engines, while maintaining good query response times. We aim to improve current state-of-the-art models used for balancing power and latency, by integratingnew advanced features. On one hand, we propose to improve the power savings by completely powering down the query servers that are not necessary when the load ofthe system is low. Besides, we consider energy rates into the model formulation. On the other hand, we focus on how to accurately estimate the latency of the whole systemby means of Queueing Theory. Experiments using actual query logs attest the high energy (and financial) savingsregarding current baselines. To the best of our knowledge, this is the first paper in successfully applying stationary Queueing Theory models to estimate the latency in alarge-scale search engine.Graz University of Technology. Institut für Informationssysteme und Computer Medien (IICM)202020202015info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttp://hdl.handle.net/10230/43870http://dx.doi.org/10.3217/jucs-021-13-1790reponame:Repositorio Digital de la UPFinstname:Universitat Pompeu FabraInglésJournal of Universal Computer Science. 2015 Jul;21(13):1790-809© Journal of Universal Computer Scienceinfo:eu-repo/semantics/openAccessoai:repositori.upf.edu:10230/438702026-06-12T07:21:37Z
dc.title.none.fl_str_mv Queuing theory-based latency/Power tradeoff models for replicated search engines
title Queuing theory-based latency/Power tradeoff models for replicated search engines
spellingShingle Queuing theory-based latency/Power tradeoff models for replicated search engines
Freire, Ana
Green IR
Information retrieval
Power consumption
Queueing theory
Search engines
title_short Queuing theory-based latency/Power tradeoff models for replicated search engines
title_full Queuing theory-based latency/Power tradeoff models for replicated search engines
title_fullStr Queuing theory-based latency/Power tradeoff models for replicated search engines
title_full_unstemmed Queuing theory-based latency/Power tradeoff models for replicated search engines
title_sort Queuing theory-based latency/Power tradeoff models for replicated search engines
dc.creator.none.fl_str_mv Freire, Ana
Macdonald, Craig
Tonellotto, Nicola
Ounis, Iadh
Cacheda, Fidel
author Freire, Ana
author_facet Freire, Ana
Macdonald, Craig
Tonellotto, Nicola
Ounis, Iadh
Cacheda, Fidel
author_role author
author2 Macdonald, Craig
Tonellotto, Nicola
Ounis, Iadh
Cacheda, Fidel
author2_role author
author
author
author
dc.subject.none.fl_str_mv Green IR
Information retrieval
Power consumption
Queueing theory
Search engines
topic Green IR
Information retrieval
Power consumption
Queueing theory
Search engines
description Large-scale search engines are built upon huge infrastructures involvingthousands of computers in order to achieve fast response times. In contrast, the energy consumed (and hence the financial cost) is also high, leading to environmental damage. This paper proposes new approaches to increase energy and financial savings in large-scale search engines, while maintaining good query response times. We aim to improve current state-of-the-art models used for balancing power and latency, by integratingnew advanced features. On one hand, we propose to improve the power savings by completely powering down the query servers that are not necessary when the load ofthe system is low. Besides, we consider energy rates into the model formulation. On the other hand, we focus on how to accurately estimate the latency of the whole systemby means of Queueing Theory. Experiments using actual query logs attest the high energy (and financial) savingsregarding current baselines. To the best of our knowledge, this is the first paper in successfully applying stationary Queueing Theory models to estimate the latency in alarge-scale search engine.
publishDate 2015
dc.date.none.fl_str_mv 2015
2020
2020
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10230/43870
http://dx.doi.org/10.3217/jucs-021-13-1790
url http://hdl.handle.net/10230/43870
http://dx.doi.org/10.3217/jucs-021-13-1790
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Journal of Universal Computer Science. 2015 Jul;21(13):1790-809
dc.rights.none.fl_str_mv © Journal of Universal Computer Science
info:eu-repo/semantics/openAccess
rights_invalid_str_mv © Journal of Universal Computer Science
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Graz University of Technology. Institut für Informationssysteme und Computer Medien (IICM)
publisher.none.fl_str_mv Graz University of Technology. Institut für Informationssysteme und Computer Medien (IICM)
dc.source.none.fl_str_mv reponame:Repositorio Digital de la UPF
instname:Universitat Pompeu Fabra
instname_str Universitat Pompeu Fabra
reponame_str Repositorio Digital de la UPF
collection Repositorio Digital de la UPF
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869407147197988864
score 15,812455

Registos relacionados