Kriging metamodeling in multi-objective simulation optimization

This paper describes an experiment exploring the potential of kriging metamodeling for multi-objective simulation optimization. The experiment studies an (s, S) inventory system with the objective of finding the optimal values of reorder point s and maximum inventory level S so as to minimize the total cost of the system while maximizing customer satisfaction. This experiment compares classical response surface methodology to kriging metamodeling as experimental approaches. The results of this experiment indicate that kriging metamodeling offers new opportunities for solving multi-objective optimization problems in stochastic simulation.