Article

Dynamic power management using machine learning

Authors:

Tajana Simunic RosingAuthors Info & Claims

ICCAD '06: Proceedings of the 2006 IEEE/ACM international conference on Computer-aided design

Pages 747 - 754

https://doi.org/10.1145/1233501.1233656

Published: 05 November 2006 Publication History

Abstract

Dynamic power management (DPM) work proposed to date places inactive components into low power states using a single DPM policy. In contrast, we instead dynamically select among a set of DPM policies with a machine learning algorithm. We leverage the fact that different policies outperform each other under different workloads and devices. Our algorithm adapts to changes in workloads and guarantees quick convergence to the best performing policy for each workload. We performed experiments with a policy set representing state of the art DPM policies on a hard disk drive and a WLAN card. Our results show that our algorithm adapts really well with changing device and workload characteristics and achieves an overall performance comparable to the best performing policy at any point of time.

References

[1]

L. Benini and G. De Micheli, Dynamic Power Management:Design Techniques and CAD Tools, Kluwer Academic Publishers, 1997.

Digital Library

[2]

Yoav Freund and Robert E. Schapire. A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences, 55(1):119--139, August 1997.

Digital Library

[3]

F. Douglis, P. Krishnan, and B. Bershad. Adaptive Disk Spin-Down Policies for Mobile Computers. In Computing Systems, volume 8, pages 381--413, 1995.

Digital Library

[4]

R. Golding, P. Bosch, and J. Wilkes. Idleness is not Sloth. In USENIX Winter Conference, pages 201--212, 1995.

Digital Library

[5]

M. B. Srivastava, A. P. Chandrakasan, and R. W. Brodersen. Predictive System Shutdown and Other Architecture Techniques for Energy Efficient Programmable Computation. IEEE Transactions on VLSI Systems, 4(1):42--55, March 1996.

Digital Library

[6]

C.-H. Hwang and A. C. Wu. A Predictive System Shutdown Method for Energy Saving of Event-Driven Computation. In International Conference on Computer-Aided Design, pages 28--32, 1997.

Digital Library

[7]

E.-Y. Chung, L. Benini, and G. D. Micheli. Dynamic power management using adaptive learning tree. In International Conference on Computer-Aided Design, pages 274--279, 1999.

Digital Library

[8]

G. A. Paleologo, L. Benini, A. Bogliolo, and G. D. Micheli. Policy Optimization for Dynamic Power Management. In Design Automation Conference, pages 182--187, 1998.

Digital Library

[9]

E.-Y. Chung, L. Benini, A. Bogliolo, and G. D. Micheli. Dynamic Power Management for Non-Stationary Service Requests. In Design Automation and Test in Europe, pages 77--81, 1999.

Digital Library

[10]

Q. Qiu and M. Pedram. Dynamic Power Management Based on Continuous-Time Markov Decision Processes. In Design Automation Conference, pages 555--561, 1999.

Digital Library

[11]

T. Simunic, L. Benini, and G. D. Micheli. Event-Driven Power Management of Portable Systems. In International Symposium on System Synthesis, pages 18--23, 1999.

Digital Library

[12]

T. Simunic, L. Benini, and G. D. Micheli. Dynamic Power Management of Laptop Hard Disk. In Design Automation and Test in Europe, 2000.

Digital Library

[13]

Yung-Hsiang Lu, Eui-Young Chung, Tajana Simunic, Luca Benini, and Giovanni De Micheli. Quantitative Comparison of Power Management Algorithms. In Design Automation and Test in Europe, pages 20--26, 2000.

Digital Library

[14]

A. Karlin, M. Manesse, L. McGeoch and S. Owicki. Competitive Randomized Algorithms for Nonuniform Problems. In Algorithmica, pp. 542--571, 1994.

[15]

C. Ruemmler and J. Wilkes. UNIX disk access patterns. In Proceedings of the Winter 1993 USENIX Conference, 1993.

[16]

Z. Ren, Krogh, B. H and Marculescu, R. Hierarchical adaptive dynamic power management. In Design Automation and Test in Europe, pages 136--141, 2004.

Digital Library

[17]

S. McFarling. Combining Branch Predictors. WRL Technical Note TN-36, Digital Equipment Corporation, June 1993.

[18]

P,-Y. Chang, E. Hao, and Y. N. Patt. Alternative Implementations of Hybrid Branch Predictors. 28^th ACM/IEEE International Symposium on Microarchitecture, Nov. 1995.

Digital Library

Cited By

Brand PFalk JSue JBrendel JHasholzner RTeich J(2018)Reinforcement Learning for Power-Efficient Grant Prediction in LTEProceedings of the 21st International Workshop on Software and Compilers for Embedded Systems10.1145/3207719.3207722(18-26)Online publication date: 28-May-2018
https://dl.acm.org/doi/10.1145/3207719.3207722
Chen ZStamoulis DMarculescu D(2018)ProfitIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems10.1109/TCAD.2017.277282237:10(2064-2075)Online publication date: 1-Oct-2018
https://dl.acm.org/doi/10.1109/TCAD.2017.2772822
Chang NMacii EPoncino MTiwari V(2016)System-Level Power ManagementElectronic Design Automation for IC System Design, Verification, and Testing10.1201/b19569-10(99-120)Online publication date: 14-Apr-2016
https://doi.org/10.1201/b19569-10
Show More Cited By

Index Terms

Dynamic power management using machine learning
1. Computing methodologies
  1. Machine learning
2. Hardware
  1. Electronic design automation
    1. Physical design (EDA)
  2. Hardware validation

Recommendations

Hybrid power management in real time embedded systems: an interplay of DVFS and DPM techniques

Energy-aware scheduling of real time applications over multiprocessor systems is considered in this paper. Early research reports that while various energy-saving policies, for instance Dynamic Power Management (DPM) and Dynamic Voltage & Frequency ...
Dynamic Power Management of Heterogeneous Systems
IPDPS '03: Proceedings of the 17th International Symposium on Parallel and Distributed Processing

Power management is critical to power-constrained real-time systems. In this paper, we present a dynamic power management algorithm for real-time heterogeneous systems. Unlike other approaches that focus on the tradeoff between power and performance, ...
Reinforcement learning based dynamic power management with a hybrid power supply
ICCD '12: Proceedings of the 2012 IEEE 30th International Conference on Computer Design (ICCD 2012)

Dynamic power management (DPM) in battery-powered mobile systems attempts to achieve higher energy efficiency by selectively setting idle components to a sleep state. However, re-activating these components at a later time consumes a large amount of ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

ICCAD '06: Proceedings of the 2006 IEEE/ACM international conference on Computer-aided design

November 2006

147 pages

ISBN:1595933891

DOI:10.1145/1233501

General Chair:
Soha Hassoun
Tufts Univ., Medford, MA

Copyright © 2006 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGDA: ACM Special Interest Group on Design Automation
IEEE-CAS: Circuits & Systems
IEEE-CS: Computer Society

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 05 November 2006

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Article

Conference

ICCAD06

Sponsor:

SIGDA
IEEE-CAS
IEEE-CS

ICCAD06: The International Conference on Computer-Aided Design 2006

November 5 - 9, 2006

California, San Jose

Acceptance Rates

Overall Acceptance Rate 457 of 1,762 submissions, 26%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

21
Total Citations
View Citations
874
Total Downloads

Downloads (Last 12 months)28
Downloads (Last 6 weeks)5

Reflects downloads up to 07 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Brand PFalk JSue JBrendel JHasholzner RTeich J(2018)Reinforcement Learning for Power-Efficient Grant Prediction in LTEProceedings of the 21st International Workshop on Software and Compilers for Embedded Systems10.1145/3207719.3207722(18-26)Online publication date: 28-May-2018
https://dl.acm.org/doi/10.1145/3207719.3207722
Chen ZStamoulis DMarculescu D(2018)ProfitIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems10.1109/TCAD.2017.277282237:10(2064-2075)Online publication date: 1-Oct-2018
https://dl.acm.org/doi/10.1109/TCAD.2017.2772822
Chang NMacii EPoncino MTiwari V(2016)System-Level Power ManagementElectronic Design Automation for IC System Design, Verification, and Testing10.1201/b19569-10(99-120)Online publication date: 14-Apr-2016
https://doi.org/10.1201/b19569-10
Gingade GChen WLu YAllebach JGutierrez-Vazquez H(2016)Hybrid Power Management for Office EquipmentACM Transactions on Design Automation of Electronic Systems10.1145/291058222:1(1-22)Online publication date: 23-Nov-2016
https://dl.acm.org/doi/10.1145/2910582
Chen ZMarculescu DNebel WAtienza D(2015)Distributed reinforcement learning for power limited many-core system performance optimizationProceedings of the 2015 Design, Automation & Test in Europe Conference & Exhibition10.5555/2755753.2757163(1521-1526)Online publication date: 9-Mar-2015
https://dl.acm.org/doi/10.5555/2755753.2757163
Triki MWang YAmmari APedram M(2015)Hierarchical power management of a system with autonomously power-managed components using reinforcement learningIntegration, the VLSI Journal10.1016/j.vlsi.2014.06.00148:C(10-20)Online publication date: 1-Jan-2015
https://dl.acm.org/doi/10.1016/j.vlsi.2014.06.001
Khan URinner B(2014)Online learning of timeout policies for dynamic power managementACM Transactions on Embedded Computing Systems10.1145/252999213:4(1-25)Online publication date: 10-Mar-2014
https://dl.acm.org/doi/10.1145/2529992
Jung HShanbhag NPoncino MChou PAmerasekera A(2012)Advanced power and thermal management for low-power, high-performance smartphonesProceedings of the 2012 ACM/IEEE international symposium on Low power electronics and design10.1145/2333660.2333741(363-364)Online publication date: 30-Jul-2012
https://dl.acm.org/doi/10.1145/2333660.2333741
Juan DMarculescu DShanbhag NPoncino MChou PAmerasekera A(2012)Power-aware performance increase via core/uncore reinforcement control for chip-multiprocessorsProceedings of the 2012 ACM/IEEE international symposium on Low power electronics and design10.1145/2333660.2333686(97-102)Online publication date: 30-Jul-2012
https://dl.acm.org/doi/10.1145/2333660.2333686
Min AWang RTsai JErgin MTai TFeo JFaraboschi PVilla O(2012)Improving energy efficiency for mobile platforms by exploiting low-power sleep statesProceedings of the 9th conference on Computing Frontiers10.1145/2212908.2212928(133-142)Online publication date: 15-May-2012
https://dl.acm.org/doi/10.1145/2212908.2212928
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Figures

Tables

Media

View Table of Conten