A mixed model for estimating the probabilistic worst case execution time

International audienceProbabilistic analysis are considered nowadays an interesting solution for real-time systems as the probabilityof appearance of worst-case values is small (10−45 per hour of functioning) compared to the acceptedprobability of failure (10−9 per hour of functioning for the highest safety level in avionics). In order to takeinto account this information, Burns and Edgar [1] have introduced the notion of probabilistic worst caseexecution time (pWCET). The pWCET of a program is bounding the probability that the execution timeof that program exceeds a given value. A possible method to estimate the pWCET is based on measurementsand the associated analysis is called measurement-based probabilistic timing analysis (MBPTA). Suchmethod has been proposed by Cucu-Grosjean et al. [2] and the obtained estimate is sensitive to the observedexecution times. To our best knowledge this dependence of MBPTA on the observations is an open problem.Within this paper we propose a first solution based on a mixed model using genetic algorithms