The main contribution of this paper is a novel hierarchical scheme for adaptive dynamic power management (DPM) under nonstationary service requests. We model the non-stationary arrival process of service requests as a Markov-modulated stochastic process in which the stochastic process for each modulation state models a particular stationary mode of the arrival process. The bottom layer of our hierarchical architecture is a set of stationary optimal DPM policies, pre-calculated off-line for selected modes from policy optimization in Markov decision processes. The supervisory power manager at the top layer adaptively and optimally switches among these stationary policies on-line to accommodate the actual mode-switching arrival dynamics. Simulation results show that our approach, under highly nonstationary requests, can lead to significant power savings compared to previously proposed heuristic approaches.
%0 Conference Paper
%1 ren2004hierarchical
%A Ren, Z.
%A Krogh, B.
%A Marculescu, R.
%B Design Automation Conference
%D 2004
%K DATE DPM Embedded Low Modelling Power Software
%T Hierarchical Adaptive Dynamic Power Management
%U http://date.eda-online.co.uk/proceedings/papers/2004/date04/pdffiles/02a_2.pdf
%X The main contribution of this paper is a novel hierarchical scheme for adaptive dynamic power management (DPM) under nonstationary service requests. We model the non-stationary arrival process of service requests as a Markov-modulated stochastic process in which the stochastic process for each modulation state models a particular stationary mode of the arrival process. The bottom layer of our hierarchical architecture is a set of stationary optimal DPM policies, pre-calculated off-line for selected modes from policy optimization in Markov decision processes. The supervisory power manager at the top layer adaptively and optimally switches among these stationary policies on-line to accommodate the actual mode-switching arrival dynamics. Simulation results show that our approach, under highly nonstationary requests, can lead to significant power savings compared to previously proposed heuristic approaches.
@inproceedings{ren2004hierarchical,
abstract = {The main contribution of this paper is a novel hierarchical scheme for adaptive dynamic power management (DPM) under nonstationary service requests. We model the non-stationary arrival process of service requests as a Markov-modulated stochastic process in which the stochastic process for each modulation state models a particular stationary mode of the arrival process. The bottom layer of our hierarchical architecture is a set of stationary optimal DPM policies, pre-calculated off-line for selected modes from policy optimization in Markov decision processes. The supervisory power manager at the top layer adaptively and optimally switches among these stationary policies on-line to accommodate the actual mode-switching arrival dynamics. Simulation results show that our approach, under highly nonstationary requests, can lead to significant power savings compared to previously proposed heuristic approaches.},
added-at = {2007-04-12T13:17:25.000+0200},
author = {Ren, Z. and Krogh, B. and Marculescu, R.},
biburl = {https://www.bibsonomy.org/bibtex/257dd7126f3c38b7d9a48907f0a4a995b/derkling},
booktitle = {Design Automation Conference},
interhash = {7aba0bdee5a51882a038213ca2408944},
intrahash = {57dd7126f3c38b7d9a48907f0a4a995b},
keywords = {DATE DPM Embedded Low Modelling Power Software},
local = {./AllPapers/2004_DATE_ren2004hierarchical.pdf},
timestamp = {2007-04-12T13:17:25.000+0200},
title = {Hierarchical Adaptive Dynamic Power Management},
url = {http://date.eda-online.co.uk/proceedings/papers/2004/date04/pdffiles/02a_2.pdf},
year = 2004
}