Leakage-Aware Energy-Efficient Scheduling of Real-Time Tasks in Multiprocessor Systems

Abstract

This work targets energy-efficient scheduling of periodic real-time tasks over multiple DVS processors with the considerations of power consumption due to leakage current. A polynomial-time algorithm with a 1.283 approximation bound is proposed when the overheads in turning on/off a processor are negligible. When the overheads are non-negligible, we develop polynomial-time algorithms with a 2 approximation bound. A series of simulation experiments was done for the performance evaluation of the proposed algorithms. The simulation results show that the proposed algorithms could derive schedules very close to optimal solutions.