Dynamic right-sizing for power-proportional data centers

Authors:
Minghong Lin;Adam Wierman;Lachlan L. H. Andrew;Eno Thereska
Affiliations:
California Institute of Technology, Pasadena, CA;California Institute of Technology, Pasadena, CA;Swinburne University of Technology, Hawthorn,Vic., Australia;Microsoft Research, Cambridge, UK
Venue:
IEEE/ACM Transactions on Networking (TON)
Year:
2013

Citing 28
Cited 0

An optimal on-line algorithm for metrical task system

Journal of the ACM (JACM)
Online computation and competitive analysis

Online computation and competitive analysis
Dynamic TCP acknowledgement and other stories about e/(e-1)

STOC '01 Proceedings of the thirty-third annual ACM symposium on Theory of computing
Managing energy and server resources in hosting centers

SOSP '01 Proceedings of the eighteenth ACM symposium on Operating systems principles
Competitive Analysis of Dynamic Power Management Strategies for Systems with Multiple Power Savings States

Proceedings of the conference on Design, automation and test in Europe
Managing server energy and operational costs in hosting centers

SIGMETRICS '05 Proceedings of the 2005 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
Reconfigurable resource scheduling

Proceedings of the eighteenth annual ACM symposium on Parallelism in algorithms and architectures
Live migration of virtual machines

NSDI'05 Proceedings of the 2nd conference on Symposium on Networked Systems Design & Implementation - Volume 2
The Case for Energy-Proportional Computing

Computer
Optimal Power-Down Strategies

SIAM Journal on Computing
Autonomic power and performance management for computing systems

Cluster Computing
Energy-aware server provisioning and load dispatching for connection-intensive internet services

NSDI'08 Proceedings of the 5th USENIX Symposium on Networked Systems Design and Implementation
Autonomic multi-agent management of power and performance in data centers

Proceedings of the 7th international joint conference on Autonomous agents and multiagent systems: industrial track
Multi-mode energy management for multi-tier server clusters

Proceedings of the 17th international conference on Parallel architectures and compilation techniques
Power and performance management of virtualized computing environments via lookahead control

Cluster Computing
Workload Analysis and Demand Prediction of Enterprise Data Center Applications

IISWC '07 Proceedings of the 2007 IEEE 10th International Symposium on Workload Characterization
Optimal power allocation in server farms

Proceedings of the eleventh international joint conference on Measurement and modeling of computer systems
SLA-Aware Virtual Resource Management for Cloud Infrastructures

CIT '09 Proceedings of the 2009 Ninth IEEE International Conference on Computer and Information Technology - Volume 02
Energy-efficient algorithms

Communications of the ACM
Semantic-less coordination of power management and application performance

ACM SIGOPS Operating Systems Review
Subjective impression of variations in layer encoded videos

IWQoS'03 Proceedings of the 11th international conference on Quality of service
Robust and flexible power-proportional storage

Proceedings of the 1st ACM symposium on Cloud computing
Optimality, fairness, and robustness in speed scaling designs

Proceedings of the ACM SIGMETRICS international conference on Measurement and modeling of computer systems
Minimizing electricity cost: optimization of distributed internet data centers in a multi-electricity-market environment

INFOCOM'10 Proceedings of the 29th conference on Information communications
Optimality analysis of energy-performance trade-off for server farm management

Performance Evaluation
Greening geographical load balancing

Proceedings of the ACM SIGMETRICS joint international conference on Measurement and modeling of computer systems
Price fluctuations: to buy or to rent

WAOA'09 Proceedings of the 7th international conference on Approximation and Online Algorithms
Online algorithms for geographical load balancing

IGCC '12 Proceedings of the 2012 International Green Computing Conference (IGCC)

Quantified Score

Hi-index	0.00

Visualization

Abstract

Power consumption imposes a significant cost for data centers implementing cloud services, yet much of that power is used to maintain excess service capacity during periods of low load. This paper investigates how much can be saved by dynamically "right-sizing" the data center by turning off servers during such periods and how to achieve that saving via an online algorithm. We propose a very general model and prove that the optimal offline algorithm for dynamic right-sizing has a simple structure when viewed in reverse time, and this structure is exploited to develop a new "lazy" online algorithm, which is proven to be 3-competitive. We validate the algorithm using traces from two real data-center workloads and show that significant cost savings are possible. Additionally, we contrast this new algorithm with the more traditional approach of receding horizon control.