APPLICATION OF KRIGING METHOD IN SURROGATE MANAGEMENT FRAMEWORK FOR OPTIMIZATION PROBLEMS

In this paper, Kriging has been chosen as the method for surrogate construction. The basic idea behind Kriging is to use a weighted linear combination of known function values to predict a function value at a place where it is not known. Kriging attempts to determine the best combination of weights in order to minimize the error in the estimated function value. Because the actual function value is not known, the error is modeled using probability theory and then minimized. The result is a linear system of equations that can be solved to find a unique combination of weights for a given point at which interpolation is to be performed.

APPLICATION OF KRIGING METHOD IN SURROGATE MANAGEMENT FRAMEWORK FOR OPTIMIZATION PROBLEMS Keywords:

Surrogate Management Framework , Kriging , Computational Order , convergence , Gradient