Adaptable mission analysis and decision system

Abstract

Discrete Event Simulation (DES) is a proven methodology that enables the effective combination of modeling and mathematics. DES has been used for many applications ranging from aeronautics to health care to transportation. In this paper, we apply a novel DES architecture that is dynamically adaptable to support decision making for multiple and diverse mission areas (i.e., missile defense, cyber offense, remote object recognition and location). This paper also advances traditional probabilistic solutions for these mission areas by extending analytics into the time domain through integration of Bayesian statistics into DES. Using DES in this way provides a straight forward way to determine the overall probabilities for a complex set of time-based events. DES also allows for random sampling of the input probability distributions and, through iterative computation, provides Monte Carlo analysis with which to derive confidence intervals for the overall probability for the simulated conditions. Confidence interval accuracy is of great importance to the simulation end-user with respect to course of action decisions.