Improving the Bounds of the Online Dynamic Power Management Problem

TL;DR

This paper improves the theoretical bounds for online algorithms in dynamic power management, specifically for a dual-machine model, by proposing a new strategy with a competitive ratio of 3 and establishing a lower bound of 2.1.

Contribution

It introduces a novel switching strategy for online power management and tightens the bounds on the competitive ratio in a dual-machine setting.

Findings

Upper bound of 3 on competitive ratio

Lower bound of 2.1 on competitive ratio

Improved bounds over previous results

Abstract

We investigate the {\em power-down mechanism} which decides when a machine transitions between states such that the total energy consumption, characterized by execution cost, idle cost and switching cost, is minimized. In contrast to most of the previous studies on the offline model, we focus on the online model in which a sequence of jobs with their release time, execution time and deadline, arrive in an online fashion. More precisely, we exploit a different switching on and off strategy and present an upper bound of 3, and further show a lower bound of 2.1, in a dual-machine model, introduced by Chen et al. in 2014 [STACS 2014: 226-238], both of which beat the currently best result.