Joint power optimization through VM placement and flow scheduling in data centers

Dawei Li, Jie Wu, Zhiyong Liu, Fa Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

4 Citations (Scopus)

Abstract

Two important components that consume the majority of IT power in data centers are the servers and the Data Center Network (DCN). Existing works fail to fully utilize power management techniques on the servers and in the DCN at the same time. In this paper, we jointly consider VM placement on servers with scalable frequencies and flow scheduling in the DCN, to minimize the overall system's power consumption. Due to the convex relation between a server's power consumption and its operating frequency, we prove that, given the number of servers to be used, computation workloads should be allocated to severs in a balanced way, to minimize the power consumption on servers. To reduce the power consumption of the DCN, we further consider the flow requirements among the VMs during VM allocation and assignment. Also, after VM placement, flow consolidation is conducted to reduce the number of active switches and ports. We notice that, choosing the minimum number of servers to accommodate the VMs may result in high power consumption on servers, due to servers' increased operating frequencies. Choosing the optimal number of servers purely based on servers' power consumption leads to reduced power consumption on servers, but may increase power consumption of the DCN. We propose to choose the optimal number of servers to be used, based on the overall system's power consumption. Simulations show that, our joint power optimization method helps to reduce the overall power consumption significantly, and outperforms various existing state-of-the-art methods in terms of reducing the overall system's power consumption.

Original languageEnglish
Title of host publication2014 IEEE 33rd International Performance Computing and Communications Conference, IPCCC 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781479975754
DOIs
StatePublished - 20 Jan 2015
Event33rd IEEE International Performance Computing and Communications Conference, IPCCC 2014 - Austin, United States
Duration: 5 Dec 20147 Dec 2014

Publication series

Name2014 IEEE 33rd International Performance Computing and Communications Conference, IPCCC 2014
Volume2014-January

Other

Other33rd IEEE International Performance Computing and Communications Conference, IPCCC 2014
CountryUnited States
CityAustin
Period5/12/147/12/14

Fingerprint

Servers
Scheduling
Electric power utilization
Consolidation
Switches

Keywords

  • Data centers
  • data center networks
  • flow scheduling
  • joint power optimization
  • virtual machine (VM) placement

Cite this

Li, D., Wu, J., Liu, Z., & Zhang, F. (2015). Joint power optimization through VM placement and flow scheduling in data centers. In 2014 IEEE 33rd International Performance Computing and Communications Conference, IPCCC 2014 [7017088] (2014 IEEE 33rd International Performance Computing and Communications Conference, IPCCC 2014; Vol. 2014-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PCCC.2014.7017088
Li, Dawei ; Wu, Jie ; Liu, Zhiyong ; Zhang, Fa. / Joint power optimization through VM placement and flow scheduling in data centers. 2014 IEEE 33rd International Performance Computing and Communications Conference, IPCCC 2014. Institute of Electrical and Electronics Engineers Inc., 2015. (2014 IEEE 33rd International Performance Computing and Communications Conference, IPCCC 2014).
@inproceedings{f0ff353b9e914f2da1304470efc3a0a3,
title = "Joint power optimization through VM placement and flow scheduling in data centers",
abstract = "Two important components that consume the majority of IT power in data centers are the servers and the Data Center Network (DCN). Existing works fail to fully utilize power management techniques on the servers and in the DCN at the same time. In this paper, we jointly consider VM placement on servers with scalable frequencies and flow scheduling in the DCN, to minimize the overall system's power consumption. Due to the convex relation between a server's power consumption and its operating frequency, we prove that, given the number of servers to be used, computation workloads should be allocated to severs in a balanced way, to minimize the power consumption on servers. To reduce the power consumption of the DCN, we further consider the flow requirements among the VMs during VM allocation and assignment. Also, after VM placement, flow consolidation is conducted to reduce the number of active switches and ports. We notice that, choosing the minimum number of servers to accommodate the VMs may result in high power consumption on servers, due to servers' increased operating frequencies. Choosing the optimal number of servers purely based on servers' power consumption leads to reduced power consumption on servers, but may increase power consumption of the DCN. We propose to choose the optimal number of servers to be used, based on the overall system's power consumption. Simulations show that, our joint power optimization method helps to reduce the overall power consumption significantly, and outperforms various existing state-of-the-art methods in terms of reducing the overall system's power consumption.",
keywords = "Data centers, data center networks, flow scheduling, joint power optimization, virtual machine (VM) placement",
author = "Dawei Li and Jie Wu and Zhiyong Liu and Fa Zhang",
year = "2015",
month = "1",
day = "20",
doi = "10.1109/PCCC.2014.7017088",
language = "English",
series = "2014 IEEE 33rd International Performance Computing and Communications Conference, IPCCC 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2014 IEEE 33rd International Performance Computing and Communications Conference, IPCCC 2014",

}

Li, D, Wu, J, Liu, Z & Zhang, F 2015, Joint power optimization through VM placement and flow scheduling in data centers. in 2014 IEEE 33rd International Performance Computing and Communications Conference, IPCCC 2014., 7017088, 2014 IEEE 33rd International Performance Computing and Communications Conference, IPCCC 2014, vol. 2014-January, Institute of Electrical and Electronics Engineers Inc., 33rd IEEE International Performance Computing and Communications Conference, IPCCC 2014, Austin, United States, 5/12/14. https://doi.org/10.1109/PCCC.2014.7017088

Joint power optimization through VM placement and flow scheduling in data centers. / Li, Dawei; Wu, Jie; Liu, Zhiyong; Zhang, Fa.

2014 IEEE 33rd International Performance Computing and Communications Conference, IPCCC 2014. Institute of Electrical and Electronics Engineers Inc., 2015. 7017088 (2014 IEEE 33rd International Performance Computing and Communications Conference, IPCCC 2014; Vol. 2014-January).

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

TY - GEN

T1 - Joint power optimization through VM placement and flow scheduling in data centers

AU - Li, Dawei

AU - Wu, Jie

AU - Liu, Zhiyong

AU - Zhang, Fa

PY - 2015/1/20

Y1 - 2015/1/20

N2 - Two important components that consume the majority of IT power in data centers are the servers and the Data Center Network (DCN). Existing works fail to fully utilize power management techniques on the servers and in the DCN at the same time. In this paper, we jointly consider VM placement on servers with scalable frequencies and flow scheduling in the DCN, to minimize the overall system's power consumption. Due to the convex relation between a server's power consumption and its operating frequency, we prove that, given the number of servers to be used, computation workloads should be allocated to severs in a balanced way, to minimize the power consumption on servers. To reduce the power consumption of the DCN, we further consider the flow requirements among the VMs during VM allocation and assignment. Also, after VM placement, flow consolidation is conducted to reduce the number of active switches and ports. We notice that, choosing the minimum number of servers to accommodate the VMs may result in high power consumption on servers, due to servers' increased operating frequencies. Choosing the optimal number of servers purely based on servers' power consumption leads to reduced power consumption on servers, but may increase power consumption of the DCN. We propose to choose the optimal number of servers to be used, based on the overall system's power consumption. Simulations show that, our joint power optimization method helps to reduce the overall power consumption significantly, and outperforms various existing state-of-the-art methods in terms of reducing the overall system's power consumption.

AB - Two important components that consume the majority of IT power in data centers are the servers and the Data Center Network (DCN). Existing works fail to fully utilize power management techniques on the servers and in the DCN at the same time. In this paper, we jointly consider VM placement on servers with scalable frequencies and flow scheduling in the DCN, to minimize the overall system's power consumption. Due to the convex relation between a server's power consumption and its operating frequency, we prove that, given the number of servers to be used, computation workloads should be allocated to severs in a balanced way, to minimize the power consumption on servers. To reduce the power consumption of the DCN, we further consider the flow requirements among the VMs during VM allocation and assignment. Also, after VM placement, flow consolidation is conducted to reduce the number of active switches and ports. We notice that, choosing the minimum number of servers to accommodate the VMs may result in high power consumption on servers, due to servers' increased operating frequencies. Choosing the optimal number of servers purely based on servers' power consumption leads to reduced power consumption on servers, but may increase power consumption of the DCN. We propose to choose the optimal number of servers to be used, based on the overall system's power consumption. Simulations show that, our joint power optimization method helps to reduce the overall power consumption significantly, and outperforms various existing state-of-the-art methods in terms of reducing the overall system's power consumption.

KW - Data centers

KW - data center networks

KW - flow scheduling

KW - joint power optimization

KW - virtual machine (VM) placement

UR - http://www.scopus.com/inward/record.url?scp=84983142781&partnerID=8YFLogxK

U2 - 10.1109/PCCC.2014.7017088

DO - 10.1109/PCCC.2014.7017088

M3 - Conference contribution

T3 - 2014 IEEE 33rd International Performance Computing and Communications Conference, IPCCC 2014

BT - 2014 IEEE 33rd International Performance Computing and Communications Conference, IPCCC 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Li D, Wu J, Liu Z, Zhang F. Joint power optimization through VM placement and flow scheduling in data centers. In 2014 IEEE 33rd International Performance Computing and Communications Conference, IPCCC 2014. Institute of Electrical and Electronics Engineers Inc. 2015. 7017088. (2014 IEEE 33rd International Performance Computing and Communications Conference, IPCCC 2014). https://doi.org/10.1109/PCCC.2014.7017088