Task Migration for Energy Conservation in Real-Time Multi-processor Embedded Systems

Abstract

In recent years, portable devices and tablet PCs grow fast and become more convenient and mobile. Applications like multimedia, SIP, and 3D movies become more diverse than before. However, the complex architecture and heavy computing demands increase energy consumption. Therefore, how to extend the standby and usage time of the devices has become an important issue. In this paper we propose a task scheduling algorithm in a real-time multi-processor system. We reduce the workload in high speed processors with the aid of task migration so that the entire system can switch to low speed as soon as it can in order to reduce energy consumption. A distinctive feature is that actual execution time is used in the decision instead of worst-case execution time, which allows for more effective task migration. Performance results based on realistic processor power consumption models are promising. Effects of parameter values on the performance are also examined.