Evaluation of Advanced Data Centre Power Management Strategies

Björn F. Postema (Corresponding Author), Boudewijn R. Haverkort (Corresponding Author)

Research output: Contribution to journalArticleAcademicpeer-review

1 Citation (Scopus)
50 Downloads (Pure)

Abstract

In recent work, we proposed a new specification language for power management strategies as an extension to our AnyLogic-based simulation framework for the trade-off analysis of power and performance in data centres. In this paper, we study the quality of such advanced power management strategies based on both power and performance measurement data collected during system operation. These strategies take a wide variety of state variables into account. In order to ensure the quality of new strategies, they are studied for stability, efficiency, adaptability and robustness; these qualities will be formally defined. This paper presents an evaluation approach for these qualities for several power management strategies inspired by strategies presented in the literature (and extensions thereof). We show that the choice of power management strategy depends both on which qualities are given the highest priority and on the used state information. The new power management strategies show significant reductions in energy consumption in our case of up to 54% energy (compared to an “always on” strategy) for a typical data centre workload for a small 30-server cluster.

Original languageEnglish
Pages (from-to)173-191
Number of pages19
JournalElectronic notes in theoretical computer science
Volume337
DOIs
Publication statusPublished - 9 May 2018
Event9th International Workshop on the Practical Application of Stochastic Modelling, PASM 2017 - Berlin, Germany
Duration: 9 Sep 20179 Sep 2017
Conference number: 9

Fingerprint

Power Management
Data Center
Evaluation
Specification languages
Servers
Energy utilization
Strategy
Power management
Simulation Framework
Performance Measurement
Specification Languages
Adaptability
Energy Consumption
Workload
Server
Trade-offs
Robustness

Keywords

  • Adaptability
  • Agent-based simulation
  • Data centre
  • Discrete-event simulation
  • Efficiency
  • Evaluation
  • Power management
  • Qualities
  • Robustness
  • Stability
  • Strategies

Cite this

@article{73158b0851ba4ac280b345319ca7f46f,
title = "Evaluation of Advanced Data Centre Power Management Strategies",
abstract = "In recent work, we proposed a new specification language for power management strategies as an extension to our AnyLogic-based simulation framework for the trade-off analysis of power and performance in data centres. In this paper, we study the quality of such advanced power management strategies based on both power and performance measurement data collected during system operation. These strategies take a wide variety of state variables into account. In order to ensure the quality of new strategies, they are studied for stability, efficiency, adaptability and robustness; these qualities will be formally defined. This paper presents an evaluation approach for these qualities for several power management strategies inspired by strategies presented in the literature (and extensions thereof). We show that the choice of power management strategy depends both on which qualities are given the highest priority and on the used state information. The new power management strategies show significant reductions in energy consumption in our case of up to 54{\%} energy (compared to an “always on” strategy) for a typical data centre workload for a small 30-server cluster.",
keywords = "Adaptability, Agent-based simulation, Data centre, Discrete-event simulation, Efficiency, Evaluation, Power management, Qualities, Robustness, Stability, Strategies",
author = "Postema, {Bj{\"o}rn F.} and Haverkort, {Boudewijn R.}",
year = "2018",
month = "5",
day = "9",
doi = "10.1016/j.entcs.2018.03.040",
language = "English",
volume = "337",
pages = "173--191",
journal = "Electronic notes in theoretical computer science",
issn = "1571-0661",
publisher = "Elsevier",

}

Evaluation of Advanced Data Centre Power Management Strategies. / Postema, Björn F. (Corresponding Author); Haverkort, Boudewijn R. (Corresponding Author).

In: Electronic notes in theoretical computer science, Vol. 337, 09.05.2018, p. 173-191.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Evaluation of Advanced Data Centre Power Management Strategies

AU - Postema, Björn F.

AU - Haverkort, Boudewijn R.

PY - 2018/5/9

Y1 - 2018/5/9

N2 - In recent work, we proposed a new specification language for power management strategies as an extension to our AnyLogic-based simulation framework for the trade-off analysis of power and performance in data centres. In this paper, we study the quality of such advanced power management strategies based on both power and performance measurement data collected during system operation. These strategies take a wide variety of state variables into account. In order to ensure the quality of new strategies, they are studied for stability, efficiency, adaptability and robustness; these qualities will be formally defined. This paper presents an evaluation approach for these qualities for several power management strategies inspired by strategies presented in the literature (and extensions thereof). We show that the choice of power management strategy depends both on which qualities are given the highest priority and on the used state information. The new power management strategies show significant reductions in energy consumption in our case of up to 54% energy (compared to an “always on” strategy) for a typical data centre workload for a small 30-server cluster.

AB - In recent work, we proposed a new specification language for power management strategies as an extension to our AnyLogic-based simulation framework for the trade-off analysis of power and performance in data centres. In this paper, we study the quality of such advanced power management strategies based on both power and performance measurement data collected during system operation. These strategies take a wide variety of state variables into account. In order to ensure the quality of new strategies, they are studied for stability, efficiency, adaptability and robustness; these qualities will be formally defined. This paper presents an evaluation approach for these qualities for several power management strategies inspired by strategies presented in the literature (and extensions thereof). We show that the choice of power management strategy depends both on which qualities are given the highest priority and on the used state information. The new power management strategies show significant reductions in energy consumption in our case of up to 54% energy (compared to an “always on” strategy) for a typical data centre workload for a small 30-server cluster.

KW - Adaptability

KW - Agent-based simulation

KW - Data centre

KW - Discrete-event simulation

KW - Efficiency

KW - Evaluation

KW - Power management

KW - Qualities

KW - Robustness

KW - Stability

KW - Strategies

U2 - 10.1016/j.entcs.2018.03.040

DO - 10.1016/j.entcs.2018.03.040

M3 - Article

VL - 337

SP - 173

EP - 191

JO - Electronic notes in theoretical computer science

JF - Electronic notes in theoretical computer science

SN - 1571-0661

ER -