An Overview of Probabilistic Performance Analysis Methods for Large Scale and Time-Dependent Systems


J. Morio, H. Piet-Lahanier, F. Poirion, J. Marzat, C. Seren, S. Bertrand, Q. Brucy, R. Kervarc, S. Merit, P. Ducourtieux, R. Pastel

PDF icon AL04-13_0.pdf4.06 MB

Various algorithms have been proposed to evaluate the performance of large scale and time-dependent systems. Probabilistic approaches based on computer experiments have been shown to be more efficient than classical approaches such as Monte-Carlo simulations for a various number of practical cases. This article thus gives an overview of the latest trends in the field, applied to the performance evaluation of large scale or time-dependent system. Different realistic applications in the aerospace domain are considered.