CAN Bus Experiments of Real-Time Communications
This paper presents a benchmark development and the analysis of communication times in a CAN (Controller Area Network) bus. Preemptive and fixed priority scheduling is taken as departure point for the initial experiments and analysis. This method would be adapted for programming CAN messages without preemption of the shared communications channel. It is also complemented by a specific priority assignment algorithm, suitable for non-preemptive systems. A real CAN network is used for the experiments, and results are analyzed from the point of view of real-time performance and CAN specification. We have found well known, deterministic, and correct performance communication times. Messages and signals are delivered within deadlines, a fundamental requirement for a real-time system.
KeywordsCAN bus implementation Real-time experiments Instrumentation and monitoring Real-time schedulability
- 1.Audsley, N.: Optimal priority assignment and feasibility of static priority tasks with arbitrary start times (1991)Google Scholar
- 3.George, L., Rivierre, N., Spuri, M.: Preemptive and non-preemptive real-time uniprocessor scheduling. Research Report RR-2966. INRIA (1996). https://hal.inria.fr/inria-00073732. projet REFLECS
- 4.Kopetz, H.: A solution to an automotive control system benchmark. In: 1994 Proceedings Real-Time Systems Symposium, pp. 154–158, December 1994Google Scholar
- 5.Lehoczky, J.P.: Fixed priority scheduling of periodic task sets with arbitrary deadlines. In: 1990 Proceedings 11th Real-Time Systems Symposium, pp. 201–209, December 1990Google Scholar
- 6.Tindell, K., Burns, A., Wellings, A.: Calculating controller area network (CAN) message response times. Control Eng. Pract. 3(8), 1163–1169 (1995). http://www.sciencedirect.com/science/article/pii/0967066195001128 CrossRefGoogle Scholar