Energy-efficient scheduling algorithm for real-time job set

Abstract

Purpose

The purpose of this paper is to investigate the scheduling problem of real-time jobs executing on a DVS processor. The jobs must complete their executions by their deadlines and the energy consumption also must be minimized.

Design/methodology/approach

The two-phase energy-efficient scheduling algorithm is proposed to solve the scheduling problem for real-time jobs. In the off-line phase, the maximum instantaneous total density and instantaneous total density (ITD) are proposed to derive the speed of the processor for each time instance. The derived speeds are saved for run time. In the on-line phase, the authors set the processor speed according to the derived speeds and set a timer to expire at the corresponding end time instance of the used speed.

Findings

When the DVS processor executes a job at a proper speed, the energy consumption of the system can be minimized.

Research limitations/implications

This paper does not consider jobs with precedence constraints. It can be explored in the further work.

Practical implications

The experimental results of the proposed schemes are presented to show the effectiveness.

Originality/value

The experimental results show that the proposed scheduling algorithm, ITD, can achieve energy saving and make the processor fully utilized.

Citation

Kuo, C.-F., Lu, Y.-F. and Chang, B.-R. (2016), "Energy-efficient scheduling algorithm for real-time job set", Engineering Computations, Vol. 33 No. 6, pp. 1753-1766. https://doi.org/10.1108/EC-08-2015-0257