A Computational Model for Real-Time Control Tasks

Background Traditional scheduling models give poor support for the design of multithreaded control systems. One difficulty lies in the nonlinearity in dynamic scheduling mechanisms such as rate-monotonic or earliest-deadline-first scheduling: a small change in a task parameter, e.g. period, execution time, deadline, priority, etc., may give rise to unpredictable results in terms of input-output latency and jitter. This is crucial, since the performance of a controller depends not only on its sampling period, but also on the inputoutput latency and the jitter. In the control design, it is straight-forward to account for a constant latency, while it is difficult to address varying or unknown delays. On the other hand, static scheduling may simplify the control design problem (because of the predictable delays) but cannot handle overruns or adaptation to changing CPU load.