Stochastic response-time guarantee for non-preemptive, fixed-priority scheduling under errors

Abstract

Error recovery mechanisms, such as automatic repeat request (ARQ) for e.g. the CAN protocol, are a crucial part of safety critical embedded systems. These can have a strong impact on the timing behavior of the system and an unpropitious combination of error events may cause a real-time application to miss deadlines with potentially hazardous consequences. Therefore, formal analysis of the worst-case timing including errors is indispensable for certification. We present a new convolution-based stochastic analysis in which we model errors as additional execution time to bound the probability for an activation to exceed a response-time value in the worst-case.