Performance Improvement of Queen-bee Genetic Algorithms through Multiple Queen-bee Evolution

Sung-Hoon Jung

Journal of The Korea Society of Computer and Information

Abbr : JKSCI
2012, 17(4), pp.129-137
Publisher : The Korean Society Of Computer And Information
Research Area : Computer Science

Sung-Hoon Jung ¹

¹한성대학교

ABSTRACT

The queen-bee genetic algorithm that we made by mimicking of the reproduction of queen-bee has considerably improved the performances of genetic algorithm. However, since we used only one queen-bee in the queen-bee genetic algorithm, a problem that individuals of genetic algorithm were driven to one place where the queen-bee existed occurred. This made the performances of the queen-bee genetic algorithm degrade. In order to solve this problem, we introduce a multiple queen-bee evolution method by employing another queen-bee whose fitness is the most significantly increased than its parents as well as the original queen-bee that is the best individual in a generation. This multiple queen-bee evolution makes the probability of falling into local optimum areas decrease and allows the individuals to easily get out of the local optimum areas even if the individuals fall into a local optimum area. This results in increasing the performances of the genetic algorithm. Experimental results with four function optimization problems showed that the performances of the proposed method were better than those of the existing method in the most cases.
KEYWORDS

Optimization, Queen-bee evolution, Multiple queen-bee evolution, Premature convergence phenomenon
REFERENCES (8)

[book] D. Goldberg / Genetic Algorithms in Search, Optimization and Machine Learning / Addison-Wesley

[journal] C. Xudong / 2001 / An Improved Genetic Algorithm for Global Optimization of Electromagnetic Problems / IEEE Trans. on Magnetics 37 : 3579~3583

[journal] Zhihua Tang / 2008 / An Elitist Selection Adaptive Genetic Algorithm for Resource Allocation in Multiuser Packet-based OFDM Systems / Journal of Communications 3(3) : 27~32

[journal] R. Poli / 2007 / Particle swarm optimization : An overview / Swarm Intelligence 1 : 33~57

[book] M. Dorigo / 2004 / Ant Colony Optimization / The MIT Press

[journal] S. H. Jung / 2003 / Queen-bee Evolution for Genetic Algorithms / Electronics Letters 39(6) : 575~576

[journal] Zhang Jinhua / 2009 / Self-organizing genetic algorithm based tuning of PID controllers / Information Sciences 179 : 1007~1018

[journal] J. Andre / 2001 / An improvement of the standard genetic algorithm fighting premature convergence in continuous optimization / Advances in engineering software 32(1) : 49~60
KCI Citation (0)

KJC Korea
Journal Central

Statistics

Tools