Construction of Confidence Absorbing Set for Analysis of Static Stochastic Systems

The problem of constructing the confidence absorbing set for the analysis of static stochastic systems is considered. The confidence absorbing set is understood as the set of initial positions for which at a terminal time instant a system will not leave an admissible domain with a given probability. Some properties of the confidence absorbing set, in particular, convexity, are established. An algorithm for constructing an inner approximation of the confidence absorbing set based on the confidence method is proposed. The properties of this approximation are established. The results obtained are used for predicting wind speed in the vicinity of a landing airfield. Calculations for a numerical experiment are presented.