Probabilistic Estimation of Response Times Through Large Deviations
Nicolas Navet, Liliana Cucu, René Schott · 2007
Abstract. We apply large deviation theory to as-sess the probability that the average, or the sum, of the response times of a sequence of consecutive ape-riodic jobs is below a given threshold. This coarse-grained performance metric is for instance adapted to gauge the responsiveness of a soft-real system or the freshness of input data consumed by an algorithm. The technique proposed works with distribution of re-sponse times as input but does not require that the dis-tribution obeys a closed-form equation. Indeed, it can accept empirical distributions given under the form of frequency histograms obtained, for instance, by mon-itoring the system. Future work should be devoted to further assess the applicability of the proposal and re-lax some technical assumptions. 1