Compositional Predictability Analysis of Mixed Critical Real Time Systems.

This paper introduces a compositional framework for analyzing the predictability of component-based embedded real-time systems. The framework utilizes automated analysis of tasks and communication architdepicts the structureectures to provide insight on the schedulability and data flow. The communicating tasks are gathered within components, making the system architecture hierarchical. The system model is given by a set of Parameterized Stopwatch Automata modeling the behavior and dependency of tasks, while we use Uppaal to analyze the predictability. Thanks to the Uppaal language, our model-based framework allows expressive modeling of the behavior. Moreover, our reconfigurable framework is customizable and scalable due to the compositional analysis. The analysis time and cost benefits of our framework are discussed through an avionic case study.