Comparative study of some algorithms for global optimization

광역최적화 방법론의 비교 연구

  • 양승호 (포항공과대학교 산업경영공학과) ;
  • 이현주 (포항공과대학교 산업경영공학과) ;
  • 이재욱 (포항공과대학교 산업경영공학과)
  • Published : 2006.11.17

Abstract

Global optimization is a method for finding more reliable models in various fields, such as financial engineering, pattern recognition, process optimization. In this study, we compare and analyze the performance of the state-of-the-art global optimization techniques, which include Genetic Algorithm (DE,SCGA), Simulated Annealing (ASA, DSSA, SAHPS), Tabu & Direct Search (DTS, DIRECT), Deterministic (MCS, SNOBIT), and Trust-Region algorithm. The test functions for the experiments are Benchmark problems in Hedar & Fukushima (2004), which are evaluated with respect to efficiency and accuracy. Through the experiment, we analyse the computational complexity of the methods and finally discuss the pros and cons of them.

Keywords