Real-time Mode-Aware Dataflow: A Dataflow Model to Specify and Analyze Mode-dependent CPSs under Relaxed Timing Constraints

원문 초록

Modern Cyber-Physical Systems (CPS) often exhibit both relaxed real-time constraints and a mode-dependent execution. Relaxed real-time constraints mean that only a subset of the processes of a CPS have real-time constraints, and a mode-dependent CPS has conditional execution branches. Static analysis tools, such as the PolyGraph model (a formalism extending the Cyclo-Static Dataflow model with real-time constraints), can specify and analyze systems with relaxed real-time constraints. However, PolyGraph is limited in its ability to specify and analyze mode-dependent CPSs. This paper extends PolyGraph with routing actors, yielding the Routed PolyGraph model. This model is further extended to the Real-time Mode-Aware Dataflow (RMDF), which both leverages routing actors and incorporates a new dataflow actor to specify mode-dependent CPSs under relaxed real-time constraints. This paper also extends the static analyses of PolyGraph to RMDF. We showcase the application of RMDF with a specification and an analysis (derivation of timing constraints at the job-level and a feasibility test) of the vision processing system of the Ingenuity Mars helicopter.