Autonomic workload and resources management of cloud computing services

Farah Fargo, Cihan Tunc, Youssif Al-Nashif, Ali Akoglu, Salim A Hariri

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

12 Citations (Scopus)

Abstract

The power consumption of data centers and cloud systems have increased almost three times between 2007 and 2012. Over-provisioning techniques are typically used for meeting the peak workloads. In this paper we present an autonomic power and performance management method for cloud systems in order to dynamically match the application requirements with 'just-enough' system resources at runtime that lead to significant power reduction while meeting the quality of service requirements of the cloud applications. Our solution offers the following capabilities: 1) real-time monitoring of the cloud resources and workload behavior running on virtual machines (VMs), 2) determine the current operating point of both workloads and the VMs running these workloads, 3) characterize workload behavior and predict the next operating point for the VMs, 4) dynamically manage the VM resources (scaling up and down the number of cores, CPU frequency, and memory amount) at run time, and 5) assign available cloud resources that can guarantee optimal power consumption without sacrificing the QoS requirements of cloud workloads. We validate the performance of our approach using the RUB is benchmark, an auction model emulating eBay transactions that generates a wide range of workloads (such as browsing and bidding with different number of clients). Our experimental results show that our approach can lead to reduction in power consumption up to 87% when compared to the static resource allocation strategy, 72% compared to adaptive frequency scaling strategy and 66% compared to a similar multi-resource management strategy.

Original languageEnglish (US)
Title of host publicationProceedings - 2014 International Conference on Cloud and Autonomic Computing, ICCAC 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages101-110
Number of pages10
ISBN (Print)9781479958412
DOIs
StatePublished - Jan 26 2015
Event2014 International Conference on Cloud and Autonomic Computing, ICCAC 2014 - London, United Kingdom
Duration: Sep 8 2014Sep 12 2014

Other

Other2014 International Conference on Cloud and Autonomic Computing, ICCAC 2014
CountryUnited Kingdom
CityLondon
Period9/8/149/12/14

Fingerprint

Cloud computing
Electric power utilization
Quality of service
Resource allocation
Program processors
Data storage equipment
Virtual machine
Monitoring

Keywords

  • AppFlow based reasoning
  • Autonomic resource management
  • Performance-per-Watt
  • power and performance management
  • workload characterization

ASJC Scopus subject areas

  • Software
  • Computer Science Applications

Cite this

Fargo, F., Tunc, C., Al-Nashif, Y., Akoglu, A., & Hariri, S. A. (2015). Autonomic workload and resources management of cloud computing services. In Proceedings - 2014 International Conference on Cloud and Autonomic Computing, ICCAC 2014 (pp. 101-110). [7024051] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCAC.2014.36

Autonomic workload and resources management of cloud computing services. / Fargo, Farah; Tunc, Cihan; Al-Nashif, Youssif; Akoglu, Ali; Hariri, Salim A.

Proceedings - 2014 International Conference on Cloud and Autonomic Computing, ICCAC 2014. Institute of Electrical and Electronics Engineers Inc., 2015. p. 101-110 7024051.

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

Fargo, F, Tunc, C, Al-Nashif, Y, Akoglu, A & Hariri, SA 2015, Autonomic workload and resources management of cloud computing services. in Proceedings - 2014 International Conference on Cloud and Autonomic Computing, ICCAC 2014., 7024051, Institute of Electrical and Electronics Engineers Inc., pp. 101-110, 2014 International Conference on Cloud and Autonomic Computing, ICCAC 2014, London, United Kingdom, 9/8/14. https://doi.org/10.1109/ICCAC.2014.36
Fargo F, Tunc C, Al-Nashif Y, Akoglu A, Hariri SA. Autonomic workload and resources management of cloud computing services. In Proceedings - 2014 International Conference on Cloud and Autonomic Computing, ICCAC 2014. Institute of Electrical and Electronics Engineers Inc. 2015. p. 101-110. 7024051 https://doi.org/10.1109/ICCAC.2014.36
Fargo, Farah ; Tunc, Cihan ; Al-Nashif, Youssif ; Akoglu, Ali ; Hariri, Salim A. / Autonomic workload and resources management of cloud computing services. Proceedings - 2014 International Conference on Cloud and Autonomic Computing, ICCAC 2014. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 101-110
@inproceedings{668df6378a67410bb08ec59469a2e857,
title = "Autonomic workload and resources management of cloud computing services",
abstract = "The power consumption of data centers and cloud systems have increased almost three times between 2007 and 2012. Over-provisioning techniques are typically used for meeting the peak workloads. In this paper we present an autonomic power and performance management method for cloud systems in order to dynamically match the application requirements with 'just-enough' system resources at runtime that lead to significant power reduction while meeting the quality of service requirements of the cloud applications. Our solution offers the following capabilities: 1) real-time monitoring of the cloud resources and workload behavior running on virtual machines (VMs), 2) determine the current operating point of both workloads and the VMs running these workloads, 3) characterize workload behavior and predict the next operating point for the VMs, 4) dynamically manage the VM resources (scaling up and down the number of cores, CPU frequency, and memory amount) at run time, and 5) assign available cloud resources that can guarantee optimal power consumption without sacrificing the QoS requirements of cloud workloads. We validate the performance of our approach using the RUB is benchmark, an auction model emulating eBay transactions that generates a wide range of workloads (such as browsing and bidding with different number of clients). Our experimental results show that our approach can lead to reduction in power consumption up to 87{\%} when compared to the static resource allocation strategy, 72{\%} compared to adaptive frequency scaling strategy and 66{\%} compared to a similar multi-resource management strategy.",
keywords = "AppFlow based reasoning, Autonomic resource management, Performance-per-Watt, power and performance management, workload characterization",
author = "Farah Fargo and Cihan Tunc and Youssif Al-Nashif and Ali Akoglu and Hariri, {Salim A}",
year = "2015",
month = "1",
day = "26",
doi = "10.1109/ICCAC.2014.36",
language = "English (US)",
isbn = "9781479958412",
pages = "101--110",
booktitle = "Proceedings - 2014 International Conference on Cloud and Autonomic Computing, ICCAC 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Autonomic workload and resources management of cloud computing services

AU - Fargo, Farah

AU - Tunc, Cihan

AU - Al-Nashif, Youssif

AU - Akoglu, Ali

AU - Hariri, Salim A

PY - 2015/1/26

Y1 - 2015/1/26

N2 - The power consumption of data centers and cloud systems have increased almost three times between 2007 and 2012. Over-provisioning techniques are typically used for meeting the peak workloads. In this paper we present an autonomic power and performance management method for cloud systems in order to dynamically match the application requirements with 'just-enough' system resources at runtime that lead to significant power reduction while meeting the quality of service requirements of the cloud applications. Our solution offers the following capabilities: 1) real-time monitoring of the cloud resources and workload behavior running on virtual machines (VMs), 2) determine the current operating point of both workloads and the VMs running these workloads, 3) characterize workload behavior and predict the next operating point for the VMs, 4) dynamically manage the VM resources (scaling up and down the number of cores, CPU frequency, and memory amount) at run time, and 5) assign available cloud resources that can guarantee optimal power consumption without sacrificing the QoS requirements of cloud workloads. We validate the performance of our approach using the RUB is benchmark, an auction model emulating eBay transactions that generates a wide range of workloads (such as browsing and bidding with different number of clients). Our experimental results show that our approach can lead to reduction in power consumption up to 87% when compared to the static resource allocation strategy, 72% compared to adaptive frequency scaling strategy and 66% compared to a similar multi-resource management strategy.

AB - The power consumption of data centers and cloud systems have increased almost three times between 2007 and 2012. Over-provisioning techniques are typically used for meeting the peak workloads. In this paper we present an autonomic power and performance management method for cloud systems in order to dynamically match the application requirements with 'just-enough' system resources at runtime that lead to significant power reduction while meeting the quality of service requirements of the cloud applications. Our solution offers the following capabilities: 1) real-time monitoring of the cloud resources and workload behavior running on virtual machines (VMs), 2) determine the current operating point of both workloads and the VMs running these workloads, 3) characterize workload behavior and predict the next operating point for the VMs, 4) dynamically manage the VM resources (scaling up and down the number of cores, CPU frequency, and memory amount) at run time, and 5) assign available cloud resources that can guarantee optimal power consumption without sacrificing the QoS requirements of cloud workloads. We validate the performance of our approach using the RUB is benchmark, an auction model emulating eBay transactions that generates a wide range of workloads (such as browsing and bidding with different number of clients). Our experimental results show that our approach can lead to reduction in power consumption up to 87% when compared to the static resource allocation strategy, 72% compared to adaptive frequency scaling strategy and 66% compared to a similar multi-resource management strategy.

KW - AppFlow based reasoning

KW - Autonomic resource management

KW - Performance-per-Watt

KW - power and performance management

KW - workload characterization

UR - http://www.scopus.com/inward/record.url?scp=84924012111&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84924012111&partnerID=8YFLogxK

U2 - 10.1109/ICCAC.2014.36

DO - 10.1109/ICCAC.2014.36

M3 - Conference contribution

AN - SCOPUS:84924012111

SN - 9781479958412

SP - 101

EP - 110

BT - Proceedings - 2014 International Conference on Cloud and Autonomic Computing, ICCAC 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -