A control-theoretic energy management for fault-tolerant hard real-time systems

Abstract

Recently, the tradeoff between low energy consumption and high fault-tolerance has attracted a lot of attention as a key issue in the design of real-time embedded systems. Dynamic Voltage Scaling (DVS) is known as one of the most effective low energy techniques for real-time systems. It has been observed that the use of control-theoretic methods can improve the effectiveness of DVS-enabled systems. In this paper, we have investigated reducing the energy consumption of fault-tolerant hard real-time systems using feedback control theory. Our proposed feedback-based DVS method makes the system capable of selecting the proper frequency and voltage settings in order to reduce the energy consumption while guaranteeing hard real-time requirements in the presence of unpredictable workload fluctuations and faults. In the proposed method, the available slack-time is exploited by a feedback-based DVS at runtime to reduce the energy consumption. Furthermore, some slack-time is reserved for re-execution in case of faults. Simulation results show that, as compared with traditional DVS methods without fault-tolerance, our proposed approach not only significantly reduces energy consumption, but also it satisfies hard real-time constraints in the presence of faults. The transition overhead (both time and energy), caused by changing the system supply voltage, are also taken into account in our simulation experiments.