CaltechAUTHORS
  A Caltech Library Service

Characterizing the impact of the workload on the value of dynamic resizing in data centers

Wang, Kai and Lin, Minghong and Ciucu, Florin and Wierman, Adam and Lin, Chuang (2012) Characterizing the impact of the workload on the value of dynamic resizing in data centers. In: SIGMETRICS '12 Proceedings of the 12th ACM SIGMETRICS/PERFORMANCE joint international conference on Measurement and Modeling of Computer Systems. ACM , New York, NY, pp. 405-406. ISBN 978-1-4503-1097-0. https://resolver.caltech.edu/CaltechAUTHORS:20170104-160858241

[img] PDF - Published Version
See Usage Policy.

756kB
[img] PDF - Submitted Version
See Usage Policy.

1MB

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20170104-160858241

Abstract

Energy consumption imposes a significant cost for data centers; yet much of that energy is used to maintain excess service capacity during periods of predictably low load. Resultantly, there has recently been interest in developing designs that allow the service capacity to be dynamically resized to match the current workload. However, there is still much debate about the value of such approaches in real settings. In this paper, we show that the value of dynamic resizing is highly dependent on statistics of the workload process. In particular, both slow time-scale non-stationarities of the workload (e.g., the peak-to-mean ratio) and the fast time-scale stochasticity (e.g., the burstiness of arrivals) play key roles. To illustrate the impact of these factors, we combine optimization-based modeling of the slow time-scale with stochastic modeling of the fast time scale. Within this framework, we provide both analytic and numerical results characterizing when dynamic resizing does (and does not) provide benefits.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://doi.org/10.1145/2254756.2254815DOIArticle
https://arxiv.org/abs/1207.6295arXivDiscussion Paper
http://resolver.caltech.edu/CaltechAUTHORS:20130109-085806826Related ItemJournal Article
http://resolver.caltech.edu/CaltechAUTHORS:20170125-151457013Related ItemConference Paper - IEEE
Additional Information:Copyright is held by the author/owner(s). This research is supported by the 973 Program of China (No. 2010CB328105), the National Natural Scientific Foundation of China (No. 61020106002 and No.60973107), and NSF grant CNS 0846025 and DoE grant DE-EE0002890.
Funders:
Funding AgencyGrant Number
973 Program of China2010CB328105
National Natural Scientific Foundation of China61020106002
National Natural Scientific Foundation of China60973107
NSFCNS-0846025
Department of Energy (DOE)DE-EE0002890
Subject Keywords:Data Centers, Dynamic Resizing, Energy Efficient IT
Classification Code:C.4 [ Performance of Systems ]: Modeling techniques
DOI:10.1145/2254756.2254815
Record Number:CaltechAUTHORS:20170104-160858241
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20170104-160858241
Official Citation:Kai Wang, Minghong Lin, Florin Ciucu, Adam Wierman, and Chuang Lin. 2012. Characterizing the impact of the workload on the value of dynamic resizing in data centers. In Proceedings of the 12th ACM SIGMETRICS/PERFORMANCE joint international conference on Measurement and Modeling of Computer Systems (SIGMETRICS '12). ACM, New York, NY, USA, 405-406. DOI=http://dx.doi.org/10.1145/2254756.2254815
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:73241
Collection:CaltechAUTHORS
Deposited By: Kristin Buxton
Deposited On:05 Jan 2017 00:18
Last Modified:11 Nov 2021 05:13

Repository Staff Only: item control page