Why statistical power matters for probabilistic real-time: work-in-progress

The probabilistic approaches for real-time systems are based on the estimation of the probabilistic-WCET distribution. Such estimation is naturally subject to errors, caused by both systematic and estimation uncertainties. To solve this problem, statistical tests are applied on the resulting distribution to check whether such errors affect or not the output validity. In this paper, we show that the reliability of these tests depends on the statistical power that must be estimated in order to select the proper sample size. This a priori analysis is required to obtain a reliable result of the probabilistic-WCET.