A survey on kriging-based infill algorithms for multiobjective simulation optimization

Abstract

This article surveys the most relevant kriging-based infill algorithms for multiobjective simulation op- timization. These algorithms perform a sequential search of so-called infill points , used to update the kriging metamodel at each iteration. An infill criterion helps to balance local exploitation and global ex- ploration during this search by using the information provided by the kriging metamodels. Most research has been done on algorithms for deterministic problem settings; only very recently, algorithms for noisy simulation outputs have been proposed. Yet, none of these algorithms so far incorporates an effective way to deal with heterogeneous noise, which remains a major challenge for future research.