Premium
An automatic control parameter tuning method for differential evolution
Author(s) -
Yamaguchi Satoshi
Publication year - 2011
Publication title -
electrical engineering in japan
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.136
H-Index - 28
eISSN - 1520-6416
pISSN - 0424-7760
DOI - 10.1002/eej.21047
Subject(s) - benchmark (surveying) , differential evolution , control (management) , process (computing) , set (abstract data type) , computer science , mathematical optimization , function (biology) , optimization problem , differential (mechanical device) , evolutionary algorithm , control theory (sociology) , mathematics , artificial intelligence , engineering , geodesy , evolutionary biology , aerospace engineering , biology , programming language , geography , operating system
Differential Evolution (DE) is an evolutionary algorithm that has shown excellent ability for solving global optimization problems over continuous spaces. DE has a few control parameters that must be set by the user. The ability of DE depends on these control parameters, and in many cases, trial‐and‐error processes are required for finding suitable values. This paper proposes a method for tuning the DE control parameters automatically. The control parameters are tuned within the DE search process. When this method is used, the finding of appropriate control parameter values by trial and error is not required. To evaluate its performance, the proposed method was applied to nine benchmark function optimization problems. The results indicate that the proposed method achieved 100% success in solving optimization problems without a major increase in the number of generations required for finding the optimum solution. © 2010 Wiley Periodicals, Inc. Electr Eng Jpn, 174(3): 25–33, 2011; Published online in Wiley Online Library ( wileyonlinelibrary.com ). DOI 10.1002/eej.21047