A Gradient Learning Optimization for Dynamic Power Management

Yanjie Li; Frank Jiang

doi:10.1109/SMC.2015.360

A Gradient Learning Optimization for Dynamic Power Management

Yanjie Li
, Frank Jiang

Harbin Institute of Technology Shenzhen
University of New South Wales

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Dynamic power management (DPM) is a power dissipation reduction technology aimed to adapting the power and performance of a system to its workload. In this paper, we propose a gradient learning optimization method for the DPM problem. Our method does not depend on accurate model parameters and is only based on a single sample path of system. Thus, there is no any transition probability to be calculated. Moreover, the new method only need less storage for the performance optimization. Simulation results demonstrate the applicability of the proposed method.

Original language	English
Title of host publication	Proceedings - 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2061-2066
Number of pages	6
ISBN (Electronic)	9781479986965
DOIs	https://doi.org/10.1109/SMC.2015.360
State	Published - 12 Jan 2016
Externally published	Yes
Event	IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015 - Kowloon Tong, Hong Kong Duration: 9 Oct 2015 → 12 Oct 2015

Publication series

Name	Proceedings - 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015

Conference

Conference	IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015
Country/Territory	Hong Kong
City	Kowloon Tong
Period	9/10/15 → 12/10/15

Keywords

gradient learning optimization
power management
time-indexed semi-Markov decision process

Access to Document

10.1109/SMC.2015.360

Cite this

Li, Y., & Jiang, F. (2016). A Gradient Learning Optimization for Dynamic Power Management. In Proceedings - 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015 (pp. 2061-2066). Article 7379492 (Proceedings - 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SMC.2015.360

@inproceedings{35cd7e17f8704181858a61ca7fff3c77,

title = "A Gradient Learning Optimization for Dynamic Power Management",

abstract = "Dynamic power management (DPM) is a power dissipation reduction technology aimed to adapting the power and performance of a system to its workload. In this paper, we propose a gradient learning optimization method for the DPM problem. Our method does not depend on accurate model parameters and is only based on a single sample path of system. Thus, there is no any transition probability to be calculated. Moreover, the new method only need less storage for the performance optimization. Simulation results demonstrate the applicability of the proposed method.",

keywords = "gradient learning optimization, power management, time-indexed semi-Markov decision process",

author = "Yanjie Li and Frank Jiang",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015 ; Conference date: 09-10-2015 Through 12-10-2015",

year = "2016",

month = jan,

day = "12",

doi = "10.1109/SMC.2015.360",

language = "英语",

series = "Proceedings - 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2061--2066",

booktitle = "Proceedings - 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015",

address = "美国",

}

Li, Y & Jiang, F 2016, A Gradient Learning Optimization for Dynamic Power Management. in Proceedings - 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015., 7379492, Proceedings - 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015, Institute of Electrical and Electronics Engineers Inc., pp. 2061-2066, IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015, Kowloon Tong, Hong Kong, 9/10/15. https://doi.org/10.1109/SMC.2015.360

A Gradient Learning Optimization for Dynamic Power Management. / Li, Yanjie; Jiang, Frank.
Proceedings - 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015. Institute of Electrical and Electronics Engineers Inc., 2016. p. 2061-2066 7379492 (Proceedings - 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Gradient Learning Optimization for Dynamic Power Management

AU - Li, Yanjie

AU - Jiang, Frank

PY - 2016/1/12

Y1 - 2016/1/12

N2 - Dynamic power management (DPM) is a power dissipation reduction technology aimed to adapting the power and performance of a system to its workload. In this paper, we propose a gradient learning optimization method for the DPM problem. Our method does not depend on accurate model parameters and is only based on a single sample path of system. Thus, there is no any transition probability to be calculated. Moreover, the new method only need less storage for the performance optimization. Simulation results demonstrate the applicability of the proposed method.

AB - Dynamic power management (DPM) is a power dissipation reduction technology aimed to adapting the power and performance of a system to its workload. In this paper, we propose a gradient learning optimization method for the DPM problem. Our method does not depend on accurate model parameters and is only based on a single sample path of system. Thus, there is no any transition probability to be calculated. Moreover, the new method only need less storage for the performance optimization. Simulation results demonstrate the applicability of the proposed method.

KW - gradient learning optimization

KW - power management

KW - time-indexed semi-Markov decision process

UR - https://www.scopus.com/pages/publications/84964502508

U2 - 10.1109/SMC.2015.360

DO - 10.1109/SMC.2015.360

M3 - 会议稿件

AN - SCOPUS:84964502508

T3 - Proceedings - 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015

SP - 2061

EP - 2066

BT - Proceedings - 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015

Y2 - 9 October 2015 through 12 October 2015

ER -

Li Y, Jiang F. A Gradient Learning Optimization for Dynamic Power Management. In Proceedings - 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015. Institute of Electrical and Electronics Engineers Inc. 2016. p. 2061-2066. 7379492. (Proceedings - 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015). doi: 10.1109/SMC.2015.360

A Gradient Learning Optimization for Dynamic Power Management

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this