Swinburne
Browse

Simple and effective dynamic provisioning for power-proportional data centers

Download (480.12 kB)
journal contribution
posted on 2024-07-11, 17:29 authored by Tan Lu, Minghua Chen, Lachlan L. H. Andrew
Energy consumption represents a significant cost in data center operation. A large fraction of the energy, however, is used to power idle servers when the workload is low. Dynamic provisioning techniques aim at saving this portion of the energy, by turning off unnecessary servers. In this paper, we explore how much gain knowing future workload information can bring to dynamic provisioning. In particular, we develop online dynamic provisioning solutions with and without future workload information available. We first reveal an elegant structure of the off-linedynamic provisioning problem, which allows us to characterize the optimal solution in a “divide-and-conquer” manner. We then exploit this insight to design two online algorithms with competitive ratios 2 ? ? and e/ (e ? 1 + ?), respectively, where 0 ? ? ? 1 is the normalized size of a look-ahead window in which future workload information is available. A fundamental observation is that future workload information beyond the fullsize look-ahead window (corresponding to ? = 1) will not improve dynamic provisioning performance. Our algorithms are decentralized and easy to implement. We demonstrate their effectiveness in simulations using real-world traces

Funding

Increasing internet energy and cost efficiency by improving higher-layer protocols

Australian Research Council

Find out more...

History

Available versions

PDF (Accepted manuscript)

ISSN

1045-9219

Journal title

IEEE Transactions on Parallel and Distributed Systems

Volume

24

Issue

6

Pagination

10 pp

Publisher

IEEE

Copyright statement

Copyright © 2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Language

eng

Usage metrics

    Publications

    Categories

    No categories selected

    Keywords

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC