A multi-fidelity surrogate-model-assisted evolutionary algorithm for computationally expensive optimization problems

Integrating data-driven surrogate models and simulation models of di erent accuracies (or delities) in a single algorithm to address computationally expensive global optimization problems has recently attracted considerable attention. However, handling discrepancies between simulation models with multiple delities in global optimization is a major challenge. To address it, the two major contributions of this paper include: (1) development of a new multidelity surrogate-model-based optimization framework, which substantially improves reliability and e ciency of optimization compared to many existing methods, and (2) development of a data mining method to address the discrepancy between the lowand highdelity simulation models. A new e cient global optimization method is then proposed, referred to as multidelity Gaussian process and radial basis function-model-assisted memetic di erential evolution. Its advantages are veri ed by mathematical benchmark problems and a real-world antenna design automation problem.