A hybrid strategy for auto-scaling of VMs: an approach based on time series and thresholds

Detalhes bibliográficos
Autor(a) principal: SILVA, Paulo Roberto Pereira da
Data de Publicação: 2019
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Repositório Institucional da UFPE
dARK ID: ark:/64986/001300000h72h
Texto Completo: https://repositorio.ufpe.br/handle/123456789/33841
Resumo: SILVA, Paulo Roberto Pereira da, também é conhecido em citações bibliográficas por: PEREIRA, Paulo
id UFPE_0645ad71146cc6cd2a54f65dd1bab8cb
oai_identifier_str oai:repositorio.ufpe.br:123456789/33841
network_acronym_str UFPE
network_name_str Repositório Institucional da UFPE
repository_id_str 2221
spelling SILVA, Paulo Roberto Pereira dahttp://lattes.cnpq.br/7559988987817463http://lattes.cnpq.br/8382158780043575MACIEL, Paulo Romero MartinsARAUJO, Jean Carlos Teixeira de2019-09-26T21:57:16Z2019-09-26T21:57:16Z2019-02-13https://repositorio.ufpe.br/handle/123456789/33841ark:/64986/001300000h72hSILVA, Paulo Roberto Pereira da, também é conhecido em citações bibliográficas por: PEREIRA, PauloDemand for performance, availability, and reliability in computational systems has increased lately. Improving these aspects is an important research challenge due to the wide diversity of applications and customers. The elasticity of cloud computing applications plays an important role, and its implementation is based on auto-scaling techniques, which allow to increase and decrease cloud-based application’s capacity. Therefore, it is possible to deal with the workload variation and not interrupt the service. The auto-scaling process can be grouped into two classes: reactive and proactive. In this dissertation, we propose a hybrid auto-scaling approach that uses reactive and proactive solutions. Our proposal is implemented using triggering thresholds and five forecasting models: Drift, Simple Exponential Smoothing, Holt, Holt-Winters and ARIMA. It checks if the CPU utilization has achieved the threshold, if it has, the system is scaled (out/in). On the other hand, if the threshold was not achieved the forecasting phase starts. In this phase, the five forecasting models are trained and tested, so the most suitable one is used to forecast resource utilization. The main goal of this research is to achieve a better QoS related to the cloud computing environment. One of the obtained results shows that our method represents a throughput improvement of 12.11% by using our proposal, instead of only using a threshold-based technique.CAPESA demanda por desempenho, disponibilidade e confiabilidade em sistemas computacionais tem aumentado bastante ultimamente. Melhorar esses aspectos é um importante desafio de pesquisa devido à grande diversidade de aplicações e usuários. A elasticidade dos aplicativos de computação em nuvem desempenha um papel importante e sua implementação é baseada em técnicas de autoescalonamento, as quais permitem aumentar e diminuir a capacidade da aplicação baseada em nuvem. Portanto, é possível lidar com a variação da carga de trabalho sem interromper o serviço. O processo de autoescalonamento pode ser agrupado em duas classes: reativo e proativo. Nesta dissertação, propomos uma abordagem híbrida de autoescalonamento que utiliza soluções reativas e proativas. Nossa proposta é implementada usando modelo reativo baseado em limiares e cinco modelos de previsão: Drift, Simple Exponential Smoothing, Holt, Holt-Winters e ARIMA. De forma que as técnicas verificam se o consumo de CPU atingiu um limiar, em caso positivo o sistema é escalonado. Por outro lado, se o limiar não foi alcançado, a fase de previsão é iniciada. Nesta fase, os cinco modelos de previsão são treinados e testados, então o mais adequado para o momento é usado para prever o consumo do recurso computacional. O principal objetivo desta pesquisa é alcançar uma melhor QoS relacionada ao ambiente de computação em nuvem. Em um dos resultados obtidos é possível notar que nosso método híbrido representa uma melhoria na vazão do sistema de 12,11% , em relação à técnica baseada nas técnicas puramente reativas.engUniversidade Federal de PernambucoPrograma de Pos Graduacao em Ciencia da ComputacaoUFPEBrasilAttribution-NonCommercial-NoDerivs 3.0 Brazilhttp://creativecommons.org/licenses/by-nc-nd/3.0/br/info:eu-repo/semantics/openAccessCiência da computaçãoComputação em nuvemA hybrid strategy for auto-scaling of VMs: an approach based on time series and thresholdsinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesismestradoreponame:Repositório Institucional da UFPEinstname:Universidade Federal de Pernambuco (UFPE)instacron:UFPETHUMBNAILDISSERTAÇÃO Paulo Roberto Pereira da Silva.pdf.jpgDISSERTAÇÃO Paulo Roberto Pereira da Silva.pdf.jpgGenerated Thumbnailimage/jpeg1239https://repositorio.ufpe.br/bitstream/123456789/33841/5/DISSERTA%c3%87%c3%83O%20Paulo%20Roberto%20Pereira%20da%20Silva.pdf.jpg746100f969d180bdad60946afd15d8abMD55ORIGINALDISSERTAÇÃO Paulo Roberto Pereira da Silva.pdfDISSERTAÇÃO Paulo Roberto Pereira da Silva.pdfapplication/pdf1283973https://repositorio.ufpe.br/bitstream/123456789/33841/1/DISSERTA%c3%87%c3%83O%20Paulo%20Roberto%20Pereira%20da%20Silva.pdfd1d17b1d13069f7686caf16ac68cb382MD51CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8811https://repositorio.ufpe.br/bitstream/123456789/33841/2/license_rdfe39d27027a6cc9cb039ad269a5db8e34MD52LICENSElicense.txtlicense.txttext/plain; charset=utf-82310https://repositorio.ufpe.br/bitstream/123456789/33841/3/license.txtbd573a5ca8288eb7272482765f819534MD53TEXTDISSERTAÇÃO Paulo Roberto Pereira da Silva.pdf.txtDISSERTAÇÃO Paulo Roberto Pereira da Silva.pdf.txtExtracted texttext/plain184896https://repositorio.ufpe.br/bitstream/123456789/33841/4/DISSERTA%c3%87%c3%83O%20Paulo%20Roberto%20Pereira%20da%20Silva.pdf.txte030f9aa838c206a2238059c93df9f67MD54123456789/338412019-10-25 10:11:14.592oai:repositorio.ufpe.br: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ório InstitucionalPUBhttps://repositorio.ufpe.br/oai/requestattena@ufpe.bropendoar:22212019-10-25T13:11:14Repositório Institucional da UFPE - Universidade Federal de Pernambuco (UFPE)false
dc.title.pt_BR.fl_str_mv A hybrid strategy for auto-scaling of VMs: an approach based on time series and thresholds
title A hybrid strategy for auto-scaling of VMs: an approach based on time series and thresholds
spellingShingle A hybrid strategy for auto-scaling of VMs: an approach based on time series and thresholds
SILVA, Paulo Roberto Pereira da
Ciência da computação
Computação em nuvem
title_short A hybrid strategy for auto-scaling of VMs: an approach based on time series and thresholds
title_full A hybrid strategy for auto-scaling of VMs: an approach based on time series and thresholds
title_fullStr A hybrid strategy for auto-scaling of VMs: an approach based on time series and thresholds
title_full_unstemmed A hybrid strategy for auto-scaling of VMs: an approach based on time series and thresholds
title_sort A hybrid strategy for auto-scaling of VMs: an approach based on time series and thresholds
author SILVA, Paulo Roberto Pereira da
author_facet SILVA, Paulo Roberto Pereira da
author_role author
dc.contributor.authorLattes.pt_BR.fl_str_mv http://lattes.cnpq.br/7559988987817463
dc.contributor.advisorLattes.pt_BR.fl_str_mv http://lattes.cnpq.br/8382158780043575
dc.contributor.author.fl_str_mv SILVA, Paulo Roberto Pereira da
dc.contributor.advisor1.fl_str_mv MACIEL, Paulo Romero Martins
dc.contributor.advisor-co1.fl_str_mv ARAUJO, Jean Carlos Teixeira de
contributor_str_mv MACIEL, Paulo Romero Martins
ARAUJO, Jean Carlos Teixeira de
dc.subject.por.fl_str_mv Ciência da computação
Computação em nuvem
topic Ciência da computação
Computação em nuvem
description SILVA, Paulo Roberto Pereira da, também é conhecido em citações bibliográficas por: PEREIRA, Paulo
publishDate 2019
dc.date.accessioned.fl_str_mv 2019-09-26T21:57:16Z
dc.date.available.fl_str_mv 2019-09-26T21:57:16Z
dc.date.issued.fl_str_mv 2019-02-13
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://repositorio.ufpe.br/handle/123456789/33841
dc.identifier.dark.fl_str_mv ark:/64986/001300000h72h
url https://repositorio.ufpe.br/handle/123456789/33841
identifier_str_mv ark:/64986/001300000h72h
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv Attribution-NonCommercial-NoDerivs 3.0 Brazil
http://creativecommons.org/licenses/by-nc-nd/3.0/br/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Attribution-NonCommercial-NoDerivs 3.0 Brazil
http://creativecommons.org/licenses/by-nc-nd/3.0/br/
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Universidade Federal de Pernambuco
dc.publisher.program.fl_str_mv Programa de Pos Graduacao em Ciencia da Computacao
dc.publisher.initials.fl_str_mv UFPE
dc.publisher.country.fl_str_mv Brasil
publisher.none.fl_str_mv Universidade Federal de Pernambuco
dc.source.none.fl_str_mv reponame:Repositório Institucional da UFPE
instname:Universidade Federal de Pernambuco (UFPE)
instacron:UFPE
instname_str Universidade Federal de Pernambuco (UFPE)
instacron_str UFPE
institution UFPE
reponame_str Repositório Institucional da UFPE
collection Repositório Institucional da UFPE
bitstream.url.fl_str_mv https://repositorio.ufpe.br/bitstream/123456789/33841/5/DISSERTA%c3%87%c3%83O%20Paulo%20Roberto%20Pereira%20da%20Silva.pdf.jpg
https://repositorio.ufpe.br/bitstream/123456789/33841/1/DISSERTA%c3%87%c3%83O%20Paulo%20Roberto%20Pereira%20da%20Silva.pdf
https://repositorio.ufpe.br/bitstream/123456789/33841/2/license_rdf
https://repositorio.ufpe.br/bitstream/123456789/33841/3/license.txt
https://repositorio.ufpe.br/bitstream/123456789/33841/4/DISSERTA%c3%87%c3%83O%20Paulo%20Roberto%20Pereira%20da%20Silva.pdf.txt
bitstream.checksum.fl_str_mv 746100f969d180bdad60946afd15d8ab
d1d17b1d13069f7686caf16ac68cb382
e39d27027a6cc9cb039ad269a5db8e34
bd573a5ca8288eb7272482765f819534
e030f9aa838c206a2238059c93df9f67
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
MD5
MD5
repository.name.fl_str_mv Repositório Institucional da UFPE - Universidade Federal de Pernambuco (UFPE)
repository.mail.fl_str_mv attena@ufpe.br
_version_ 1815172825759088640

Registros relacionados