Online Energy-Efficient Hard Real-Time Scheduling for Component Oriented Systems

Abstract

The energy efficiency becomes one of the most important concerns in mobile electronic systems design with mandatory requirements for low energy consumption, long battery life and low heat dissipation. Dynamic Power Management (DPM) and Dynamic Voltage and Frequency Scaling (DVFS or DVS) are two widely applied system level techniques to conserve system-wide power consumption. In the context of hard real-time systems, however, DPM and DVS have to be used with great caution in terms of timing constraints. In this article, we study the combined application of DPM and DVS for component oriented systems with hard real-time tasks and propose a simulated annealing based optimization algorithm and its online execution with constant complexity at each scheduling point. Additionally, our approach considers multiple low power states (sleep states) with non-negligible switching overhead. The experimental results show that our approach can achieve almost an optimal solution.