Logistic Characteristic Curves (LCCs) or Logistic Operating
Curves (LOCs) describe relationships between various Key Performance Indicators
(KPIs) of production and logistics systems. These relationships can be
qualitatively or quantitatively visualized by charts to illustrate the
performance of these systems. Discrete Event Simulation (DES) allows a detailed
investigation of the dynamic behavior of production and logistics systems under
consideration of uncertainties and thus contributes to their planning
reliability. Using simulation models and the data generated by the experiments,
KPIs of the modeled systems are measured. Of course, different production and
logistics systems also have several target systems whereby the individual
target variables interact with each other and can, therefore, conflict. In this
paper, a methodology is presented that combines DES and a statistical technique
for empirical model building, namely the response surface model, to predict the
behavior of production and logistics systems by using LOCs and thereby decrease
the effort for experimentation by reducing the number of simulation runs.