Energy-aware primary/backup scheduling of periodic real-time tasks on heterogeneous multicore systems

For real-time embedded systems, energy management and fault tolerance are both critical. However these two objectives are often at odds, because extra resources needed to tolerate faults significantly increase the energy consumption. In this paper, we consider energy-aware and fault-tolerant scheduling of periodic real-time tasks. Our target platform is a heterogeneous multicore system. We reduce the energy consumption by both applying DVFS to scale the primary tasks, and maximizing the opportunities to cancel the back-up tasks in fault-free execution scenarios. To tolerate both transient and permanent faults, primary and backup copies of tasks are scheduled on different cores. Our framework consists of offline and online phases to manage energy and fault-tolerant scheduling of periodic tasks in tandem. The latter objective is achieved through an explicit task prior -ity assignment phase, coupled with a dual queue based back-up delaying algorithm. In particular, we propose a scheme called Reverse Preference-Oriented Priority Assignment (RPPA) which is experimentally shown to be very effective to reduce the energy consumption. RPPA, when coupled with the dual-queue based delaying algorithm, outperforms other schemes and approaches the energy performance of a theoretical lower bound. All the pro-posed schemes satisfy the stringent timing and fault tolerance requirements of periodic real-time tasks while managing the energy consumption dynamically.