Input uncertainty quantification for simulation models with piecewise-constant non-stationary Poisson arrival processes

摘要

Input uncertainty (IU) is the outcome of driving simulation models using input distributions estimated by finite amounts of real-world data. Methods have been presented for quantifying IU when stationary input distributions are used. In this paper we extend upon this work and provide two methods for quantifying IU in simulation models driven by piecewise-constant non-stationary Poisson arrival processes. Numerical evaluation and illustrations of the methods are provided and indicate that the methods perform well.