Schedulability analysis for CAN bus messages of periodically-varying size
Ishfaq Hussain, Pedro F. Souto, Konstantinos Bletsas, Muhammad Ali Awan, Eduardo Tovar · 2022
Conventional CAN bus schedulability analysis as-sumes that all messages with a given identifier have the same worst-case length. In this paper we extend that analysis to a more general model in which messages with a given identifier may have different lengths, that vary according to a known periodic pattern. That is, for some positive integer$s$, we assume that the length of message instances$n$and$n+S$with the same id is the same. By leveraging such patterns, where present, our new analysis allows for a more efficient use of CAN bus bandwidth than the application of conventional analysis, which can be pessimistic. This may be interesting when a given node sends the values of multiple signals with different periods. In such a scenario, the conventional CAN schedulability analysis would require either the use of different ids for different signals (assuming there are enough of them), which leads to a higher bandwidth overhead because of the reduplication of message headers, or using only one id, but pessimistically always assuming the maximum possible length of the message, for safety reasons.