Energy Minimization for Software Real-Time Systems with Uncertain Execution Time

Abstract

Energy-saving is extraordinary important for real-time systems. Dynamic Voltage Scaling as one of the prime and effective techniques is popular with tasks scheduling. Due to un-ignorable frequency tradeoff, even some strategies consider the penalty, deadline misses occur frequently and produces much extra energy dissipation. In this paper, we propose an optimal soft real-time dynamic program scheme by using quantitative switch tradeoff for multitasks scheduling with uncertain execution time. The simulation results show that our approach achieves significant energy-saving than existing solutions.