Determining the Optimal Timeout Values for a Power-Managed System based on the Theory of Markovian Processes: Offline and Online Algorithms

This paper presents a timeout-driven DPM technique which relies on the theory of Markovian processes. The objective is to determine the energy-optimal timeout values for a system with multiple power saving states while satisfying a set of user defined performance constraints. More precisely, a controllable Markovian process is exploited to model the power management behavior of a system under the control of a timeout policy. Starting with this model, a perturbation analysis technique is applied to develop an offline gradient-based approach to determine the optimal timeout values. Online implementation of this technique for a system with dynamically-varying system parameters is also described. Experimental results demonstrate the effectiveness of the proposed approach. Introduction Dynamic power management (DPM), which refers to selective shut-off or slow-down of components that are idle or underutilized, has proven to be a particularly effective technique for reducing power dissipation in such systems. In the literature, various DPM techniques have been proposed, from heuristic methods presented in early works [ 1][ 2] to stochastic optimization approaches [ 3][ 4]. Among the heuristic DPM methods, the timeout policy is the most widely used approach in industry and has been implemented in many operating systems. Examples include the power management scheme incorporated into the Windows system, the low-power saving mode of the IEEE 802.11a-g protocol for wireless LAN card, and the enhanced adaptive battery life extender (EABLE) for the Hitachi disk drive. Most of these industrial DPM techniques provide mechanisms to adjust the timeout values at the user level.