Power Efficient Scheduling for Hard Real-Time Systems on a Multiprocessor Platform

An online, real-time scheduler is proposed to minimize the power consumption of a task set during execution on a multiprocessor platform. The scheduler is capable of handling the spectrum of task types (periodic, sporadic, and aperiodic) as well as supporting mutually exclusive, shared resources. The solution presented is a user adjustable scheduler which ranges from producing an optimal schedule which requires the minimum power during the worst case execution scenario to producing a suboptimal schedule which aggressively minimizes power during the typical execution scenario.