Towards an energy-efficient quarter-clairvoyant mixed-criticality system

Abstract

Mode switch is the key strategy in mixed-criticality systems, enabling a dynamic balance between system performance and safety. Mode switch in conventional MCS frameworks is always triggered by over-execution of a task, i.e., a task overrunning the less pessimistic worst-case execution time. In cyber–physical systems, the data volume generated by I/O affects and even dominates task execution time. Based on this observation, we propose a novel MCS framework, named Pythia-MCS, which predicts task execution time according to I/O run-time behaviors. With the new feature of future-prediction, Pythia-MCS provides more timely, but still accurate, mode switches. We specifically introduce the Pythia-MCS design methods, including different allocations of I/O monitoring and an efficient energy management framework. We present a new theoretical model (quarter-clairvoyance), which guarantees the timing predictability of the design, and a new schedulability analysis for Pythia-MCS, which demonstrates improved schedulability compared to conventional MCS frameworks. In addition, Pythia-MCS is comprehensively evaluated using a number of metrics.