Q-DPM: An Efficient Model-Free Dynamic Power Management Technique

TL;DR

This paper introduces Q-DPM, a model-free dynamic power management method using Q-Learning, designed for low-end embedded systems to efficiently adapt to changing conditions without complex modeling.

Contribution

It presents a novel, efficient model-free DPM approach that eliminates parameter estimation overhead and enables rapid adaptation through online trialing.

Findings

Q-DPM reduces overhead compared to model-based methods.

It responds quickly to time-varying system behavior.

Demonstrates improved efficiency in embedded systems.

Abstract

When applying Dynamic Power Management (DPM) technique to pervasively deployed embedded systems, the technique needs to be very efficient so that it is feasible to implement the technique on low end processor and tight-budget memory. Furthermore, it should have the capability to track time varying behavior rapidly because the time varying is an inherent characteristic of real world system. Existing methods, which are usually model-based, may not satisfy the aforementioned requirements. In this paper, we propose a model-free DPM technique based on Q-Learning. Q-DPM is much more efficient because it removes the overhead of parameter estimator and mode-switch controller. Furthermore, its policy optimization is performed via consecutive online trialing, which also leads to very rapid response to time varying behavior.