Scheduling Mixed-Criticality Systems on Varying-Speed Processors: A Meta-Reinforcement Learning Approach for Non-Preemptive Tasks

Abstract

Mixed-Criticality (MC) systems have to guarantee the timely execution of high-criticality tasks even under adversarial processor conditions. Prior work addresses preemptive scheduling, leaving the NP hard, non-preemptive scheduling problem unexplored. This paper presents a novel Meta-Reinforcement Learning (Meta-RL) framework that serves as an adaptive scheduler selector for offline, non-preemptive MC scheduling on processors subject to stochastic degradation. Our work develops a pretrained RL-based scheduler that is capable of handling adversarial workloads, where classical algorithms, such as Earliest Deadline First (EDF), would fail, and then integrates this RL scheduler into a meta-agent that is able to select between Earliest Deadline First (EDF) and the RL scheduler based on workload characteristics. Our approach builds on the degradation model found by Baruah et al. (2014). Extensive Experiments across 1,000,000 + instances demonstrate that the Meta-RL framework achieves higher criticality than EDF in the presence of adversarial instances. Our results establish Meta-RL as a robust and adaptive solution for mixed-criticality scheduling under realistic processor behavior, opening the door for future work on online variants and scalable RL-based scheduling algorithms.