EDF-based Energy-Efficient Probabilistic Imprecise Mixed-Criticality Scheduling

We focus on Mixed-Criticality Systems (MCS), which involves the integration of multiple subsystems with varying levels of criticality on shared hardware platforms. The classic MCS task model assumes hard real-time constraints and no Quality-of-Service (QoS) for low-criticality tasks in high-criticality mode. Many researchers have put forward a range of extensions to the classic MCS task model to make MCS theory more applicable in industry practice. In this paper, we consider an Imprecise MCS taskset scheduled with Earliest Deadline First algorithm on a uniprocessor platform, and propose an Energy-Efficient Task Execution Model that guarantees (deterministic or probabilistic) schedulability, allows degraded QoS to low-criticality tasks in high-criticality mode, and applies Dynamic Voltage and Frequency Scaling to save energy.