Enabling scheduling analysis of heterogeneous systems with multi-rate data dependencies and rate intervals

Formal methods are growing in importance for performance analysis of real-time systems, but embedded system heterogeneity limits the application of these methods to subsystems or special cases. One of the problems is the rich variety of interactions between embedded system processes, which cannot be directly expressed with the typical event models used in real-time analysis. This paper shows how to transform complex interaction patterns into the integral representation of minimum and maximum arrival curves, and then to conservatively approximate these arrival curves using standard event models. This approach paves the way to apply the formal approaches known from real-time analysis to heterogeneous embedded systems.