DocumentCode :
463666
Title :
Time Series Modeling Based Power and Performance Scaling Framework
Author :
Khan, Muhammad H. ; Yu Bai ; Bin Xiao ; Vaidya, P.N.
Volume :
2
fYear :
2007
fDate :
15-20 April 2007
Abstract :
This paper enhances a software based framework to dynamically scale power and performance with high accuracy in a resource limited embedded system, like cellular phones and PDAs. Key challenges for such a framework are accurate forecasting of dynamic resource demands inherent in the workloads. In this paper we describe three innovative methods: (1) smart forecast method based on linear and non-linear filtering models; (2) policy decision based on high fidelity memory and computation characterization; and (3) adaptive sampling period to adapt to dynamic changes in the workloads. Power and performance framework driven by the proposed algorithms reduces power consumption thus improving battery lifetime for the end-user.
Keywords :
cellular radio; nonlinear filters; notebook computers; operating systems (computers); telecommunication computing; time series; PDA; adaptive sampling period; cellular phones; computation characterization; dynamic performance scaling framework; dynamic power scaling framework; dynamic resource demands; high fidelity memory; linear filtering model; nonlinear filtering model; policy decision; resource limited embedded system; smart forecast method; software based framework; time series modeling; Adaptive filters; Cellular phones; Demand forecasting; Embedded software; Embedded system; Nonlinear dynamical systems; Nonlinear filters; Personal digital assistants; Power system modeling; Software performance; Embedded Multimedia; Low Power Multi-media; System Modeling;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech and Signal Processing, 2007. ICASSP 2007. IEEE International Conference on
Conference_Location :
Honolulu, HI
ISSN :
1520-6149
Print_ISBN :
1-4244-0727-3
Type :
conf
DOI :
10.1109/ICASSP.2007.366250
Filename :
4217423
Link To Document :
بازگشت