Energy-efficient scheduling for stability-guaranteed embedded control systems

Abstract

Stability, which is heavily dependent on the controller delays, is the main measure of performance in embedded control systems. With the increased demand for resources in such systems, energy consumption has been converted to an important issue, especially in systems with limited energy sources like batteries. Accordingly, in addition to the traditional temporal requirements in these systems, stability and economic energy usage are further demands for the design of embedded control systems. For the latter demand, dynamic voltage and frequency scaling (DVFS) is too usual, however, as this technique increases the controller delay and jitter, it may negatively impact the system stability. This paper addresses the problem of control task priority assignment as well as task-specific processor voltage/ frequency assignment such that the stability be guaranteed and the energy consumption be reduced. The proposed idea considers the task execution-time variability and increases the processor frequency only when the task execution-time exceeds some threshold. Experimental results show energy-efficiency of the proposed method for embedded control systems.