A New Perspective on Quality Evaluation for Control Systems with Stochastic Timing

As control applications are particularly sensitive to timing variations, the Quality of Control (QoC) is degraded by varying execution conditions of the underlying real-time system. In particular, transitions between different execution or environmental conditions pose a significant issue as they may impact the QoC unexpectedly. So far, the QoC is usually evaluated either in a stationary, time-invariant way, which cannot analyze said transitions, or by simulation, which becomes inefficient when confronted with random influencing factors. In this paper, we propose a new perspective on QoC evaluation for modern, adaptive real-time systems with varying timing conditions. For this, we present a time-variant stochastic assessment approach that incorporates the effects mentioned before. Our results demonstrate that adaptive scheduling and runtime behavior considerably impacts the QoC. At the same time, the proposed scheme significantly outperforms a traditional simulation.