Auto-Scaling Provision Basing on Workload Prediction in the Virtualized Data Center

IF 0.6 Q4 COMPUTER SCIENCE, THEORY & METHODS International Journal of Grid and High Performance Computing Pub Date : 2020-01-01 DOI:10.4018/ijghpc.2020010104

Danqing Feng, Zhibo Wu, Decheng Zuo, Zhan Zhang

{"title":"Auto-Scaling Provision Basing on Workload Prediction in the Virtualized Data Center","authors":"Danqing Feng, Zhibo Wu, Decheng Zuo, Zhan Zhang","doi":"10.4018/ijghpc.2020010104","DOIUrl":null,"url":null,"abstract":"WiththedevelopmentintheClouddatacenters,thepurposeoftheefficientresourceallocationis tomeetthedemandoftheusersinstantlywiththeminimumrentcost.Thus,theelasticresource allocationstrategyisusuallycombinedwiththepredictiontechnology.Thisarticleproposesanovel predictmethodcombinationforecasttechnique,includingbothexponentialsmoothing(ES)andautoregressiveandpolynomialfitting(PF)model.Theaimofcombinationpredictionistoachievean efficientforecasttechniqueaccordingtotheperiodicandrandomfeatureoftheworkloadandmeet theapplicationservicelevelagreement(SLA)withtheminimumcost.Moreover,theESprediction withPSOalgorithmgivesafine-grainedscalingupanddowntheresourcescombiningtheheuristic algorithminthefuture.APWPwouldsolvetheperiodicalorhybridfluctuationoftheworkloadin theclouddatacenters.Finally,experimentsimprovethatthecombinedpredictionmodelmeetsthe SLAwiththebetterprecisionaccuracywiththeminimumrentingcost. KeyWoRDS ES, PF, Prediction, Provisioning, Scaling, SLA","PeriodicalId":43565,"journal":{"name":"International Journal of Grid and High Performance Computing","volume":"76 1","pages":"53-69"},"PeriodicalIF":0.6000,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Grid and High Performance Computing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4018/ijghpc.2020010104","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"COMPUTER SCIENCE, THEORY & METHODS","Score":null,"Total":0}

引用次数: 2

Abstract

WiththedevelopmentintheClouddatacenters,thepurposeoftheefficientresourceallocationis tomeetthedemandoftheusersinstantlywiththeminimumrentcost.Thus,theelasticresource allocationstrategyisusuallycombinedwiththepredictiontechnology.Thisarticleproposesanovel predictmethodcombinationforecasttechnique,includingbothexponentialsmoothing(ES)andautoregressiveandpolynomialfitting(PF)model.Theaimofcombinationpredictionistoachievean efficientforecasttechniqueaccordingtotheperiodicandrandomfeatureoftheworkloadandmeet theapplicationservicelevelagreement(SLA)withtheminimumcost.Moreover,theESprediction withPSOalgorithmgivesafine-grainedscalingupanddowntheresourcescombiningtheheuristic algorithminthefuture.APWPwouldsolvetheperiodicalorhybridfluctuationoftheworkloadin theclouddatacenters.Finally,experimentsimprovethatthecombinedpredictionmodelmeetsthe SLAwiththebetterprecisionaccuracywiththeminimumrentingcost. KeyWoRDS ES, PF, Prediction, Provisioning, Scaling, SLA

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

虚拟化数据中心中基于工作负载预测的自动伸缩发放

WiththedevelopmentintheClouddatacenters，thepurposeoftheefficientresourceallocationis tomeetthedemandoftheusersinstantlywiththeminimumrentcost。Thus，theelasticresource allocationstrategyisusuallycombinedwiththepredictiontechnology。Thisarticleproposesanovel predictmethodcombinationforecasttechnique、includingbothexponentialsmoothing(ES)andautoregressiveandpolynomialfitting(PF)modelTheaimofcombinationpredictionistoachievean efficientforecasttechniqueaccordingtotheperiodicandrandomfeatureoftheworkloadandmeet theapplicationservicelevelagreement(SLA)withtheminimumcost。Moreover，theESprediction withPSOalgorithmgivesafine-grainedscalingupanddowntheresourcescombiningtheheuristic algorithminthefuture。APWPwouldsolvetheperiodicalorhybridfluctuationoftheworkloadin theclouddatacenters。Finally，experimentsimprovethatthecombinedpredictionmodelmeetsthe SLAwiththebetterprecisionaccuracywiththeminimumrentingcost。关键词ES, PF，预测，预置，缩放，SLA

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊