Computing a language-based guarantee for timing properties of cyber-physical systems

Real-time systems are often guaranteed in terms of schedulability, which verifies whether or not all jobs meet their deadlines. However, such a guarantee can be insufficient in certain applications. In this paper, we propose a method to compute a language-based guarantee which provides a more detailed description of the deadline miss patterns of an observed task. The only requirement of our method is that the timing behavior of the real-time system be modelled by a network of timed automata. We compute the language-based guarantee by constructing an equivalent finite state automaton in an iterative manner, using a counter-example guided procedure. We illustrate the language-based guarantee for two applications: design of a networked control system and scheduling in a mixed criticality system. In both cases, we show that the language-based guarantee leads to a more efficient design than the schedulability guarantee.