A New Filled Function for Global Optimization

Abstract

The filled function method has recently become very popular in optimization theory, as it is an e cient and e ective method for finding the global minimizer of multimodal functions. However, the fact that the existing filled functions in the literature generally have exponential or logarithmic terms and/or parameter sensitivity reduces the e ectiveness of this method. In this study, we propose a new non parameter and without exponential/logarithmic terms filled function, which is numerically stable, and is successfully used to solve global optimization problems. Furthermore, we have demonstrated how successful this new filled function method in terms of e ciency with numerical experiments and comparisons.

Keywords

• global optimization
• filled function method
• auxiliary function
• bezier curve
• primary 90c26, 65k05
• secondary 90c30, 65k10, 65d10