Open AccessA Surrogate Model Based Genetic Algorithm for Complex Problem Solving
Author(s) -
Ying Pei,
Hao Gao,
Xiaosong Han
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1646/1/012153
Subject(s) - benchmark (surveying) , fitness function , genetic algorithm , fitness approximation , computer science , mathematical optimization , surrogate model , artificial neural network , algorithm , meta optimization , population based incremental learning , artificial intelligence , machine learning , mathematics , geodesy , geography
It is well known that when the fitness function is relatively complex, the optimization time cost of the genetic algorithm will be extremely huge. To address this issue, the surrogate model was employed to predict the fitness value of the optimization problem, to reduce the number of actual calculated fitness values. In this paper, BP neural network, the least square method and support vector machine were fused in the genetic algorithm to evaluate partial individuals’ fitness. Sufficient benchmark numerical experiments were conducted, and the results proved that the strategy could reduce the calculating counts of fitness function on similar accuracy basis compared with simple genetic algorithm.