Computationally expensive multiobjective optimization problems arise, e.g. in many engineeringapplications, where several conflicting objectives are to be optimized simultaneouslywhile satisfying constraints. In many cases, the lack of explicit mathematical formulasof the objectives and constraints may necessitate conducting computationally expensive andtime-consuming experiments and/or simulations. As another challenge, these problems mayhave either convex or nonconvex or even disconnected Pareto frontier consisting of Paretooptimal solutions. Because of the existence of many such solutions, typically, a decisionmaker is required to select the most preferred one. In order to deal with the high computationalcost, surrogate-based methods are commonly used in the literature. This papersurveys surrogate-based methods proposed in the literature, where the methods are independentof the underlying optimization algorithm and mitigate the computational burden tocapture different types of Pareto frontiers. The methods considered are classified, discussedand then compared. These methods are divided into two frameworks: the sequential andthe adaptive frameworks. Based on the comparison, we recommend the adaptive frameworkto tackle the aforementioned challenges.
展开▼
