A Combined Frequency Scaling and Application Elasticity Approach for Energy-Efficient Virtualized Data Centers

At present, large-scale data centers are typically over-provisioned in order to handle peak load requirements. The resulting low utilization of resources contribute to a huge amounts of power consumption in data centers. The effects of high power consumption manifest in a high operational cost in da...

Full description

Bibliographic Details
Main Author: Tesfatsion Kostentinos, Selome
Format: Others
Language:English
Published: Umeå universitet, Institutionen för datavetenskap 2013
Online Access:http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-85211
id ndltd-UPSALLA1-oai-DiVA.org-umu-85211
record_format oai_dc
spelling ndltd-UPSALLA1-oai-DiVA.org-umu-852112014-01-31T04:50:34ZA Combined Frequency Scaling and Application Elasticity Approach for Energy-Efficient Virtualized Data CentersengTesfatsion Kostentinos, SelomeUmeå universitet, Institutionen för datavetenskap2013At present, large-scale data centers are typically over-provisioned in order to handle peak load requirements. The resulting low utilization of resources contribute to a huge amounts of power consumption in data centers. The effects of high power consumption manifest in a high operational cost in data centers and carbon footprints to the environment. Therefore, the management solutions for large-scale data centers must be designed to effectively take power consumption into account. In this work, we combine three management techniques that can be used to control systems in an energy-efficient manner: changing the number of virtual machines, changing the number of cores, and scaling the CPU frequencies. The proposed system consists of a controller that combines feedback and feedforward information to determine a configuration that minimizes power consumption while meeting the performance target. The controller can also be configured to accomplish power minimization in a stable manner, without causing large oscillations in the resource allocations. Our experimental evaluation based on the Sysbench benchmark combined with workload traces from production systems shows that our approach achieves the lowest energy consumption among the compared three approaches while meeting the performance target. Student thesisinfo:eu-repo/semantics/bachelorThesistexthttp://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-85211UMNAD ; 973application/pdfinfo:eu-repo/semantics/openAccess
collection NDLTD
language English
format Others
sources NDLTD
description At present, large-scale data centers are typically over-provisioned in order to handle peak load requirements. The resulting low utilization of resources contribute to a huge amounts of power consumption in data centers. The effects of high power consumption manifest in a high operational cost in data centers and carbon footprints to the environment. Therefore, the management solutions for large-scale data centers must be designed to effectively take power consumption into account. In this work, we combine three management techniques that can be used to control systems in an energy-efficient manner: changing the number of virtual machines, changing the number of cores, and scaling the CPU frequencies. The proposed system consists of a controller that combines feedback and feedforward information to determine a configuration that minimizes power consumption while meeting the performance target. The controller can also be configured to accomplish power minimization in a stable manner, without causing large oscillations in the resource allocations. Our experimental evaluation based on the Sysbench benchmark combined with workload traces from production systems shows that our approach achieves the lowest energy consumption among the compared three approaches while meeting the performance target.
author Tesfatsion Kostentinos, Selome
spellingShingle Tesfatsion Kostentinos, Selome
A Combined Frequency Scaling and Application Elasticity Approach for Energy-Efficient Virtualized Data Centers
author_facet Tesfatsion Kostentinos, Selome
author_sort Tesfatsion Kostentinos, Selome
title A Combined Frequency Scaling and Application Elasticity Approach for Energy-Efficient Virtualized Data Centers
title_short A Combined Frequency Scaling and Application Elasticity Approach for Energy-Efficient Virtualized Data Centers
title_full A Combined Frequency Scaling and Application Elasticity Approach for Energy-Efficient Virtualized Data Centers
title_fullStr A Combined Frequency Scaling and Application Elasticity Approach for Energy-Efficient Virtualized Data Centers
title_full_unstemmed A Combined Frequency Scaling and Application Elasticity Approach for Energy-Efficient Virtualized Data Centers
title_sort combined frequency scaling and application elasticity approach for energy-efficient virtualized data centers
publisher Umeå universitet, Institutionen för datavetenskap
publishDate 2013
url http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-85211
work_keys_str_mv AT tesfatsionkostentinosselome acombinedfrequencyscalingandapplicationelasticityapproachforenergyefficientvirtualizeddatacenters
AT tesfatsionkostentinosselome combinedfrequencyscalingandapplicationelasticityapproachforenergyefficientvirtualizeddatacenters
_version_ 1716633586048696320