Best model optimization gives a condensed introduction to simulation-based optimization methods, based on the content of the more elaborate and in-depth overview. Many stochastic optimization problems encountered in real-world applications are too complex to be described in closed-form mathematical models and solved analytically. One approach for tackling such problems is to use simulation. The purpose of simulation models is to forecast the behavior of complex, stochastic, real-world systems. Usually, simulation models are used to evaluate the consequences of single decision alternatives without implementing these in the real-world system, as this might result in negative effects. Simulation models can be categorized along the following three dimensions: - Static vs. dynamic simulation models: A static simulation model represents a system by a “snapshot” at a certain point in time, whereas a dynamic simulation model maps a system’s behavior over time. - Deterministic vs. stochastic simulation models: If a simulation model does not contain any random influences, it is termed deterministic, and otherwise stochastic.