Using selection to improve quantum-behaved particle swarm optimisation. (25th February 2010)

• Record Type: Journal Article
• Authors: Long, Haixia; Sun, Jun; Wang, Xiaogen; Lai, C-H.; , Wenbo Xu
• Is Part Of: International journal of innovative computing and applications. Volume 2:Number 2(2009)
• Page Start: 100
• Page End: 114
• Publication Date: 2010-02-25
• Subjects: quantum-behaved particle swarm optimisation -- QPSO -- tournament selection -- roulette-wheel selection -- global best position -- QPSO-TS -- QPSO-R -- search abilityS; Evolutionary computation -- Periodicals; Neural networks (Computer science) -- Periodicals; Genetic programming (Computer science) -- Periodicals; Biologically-inspired computing -- Periodicals; Swarm intelligence -- Periodicals; Quantum computers -- Periodicals; 006.3
• Languages: English
• ISSNs: 1751-648X

Abstract

Quantum-behaved particle swarm optimisation (QPSO) algorithm is a global convergence guaranteed algorithms, which outperforms original PSO in search ability but has fewer parameters to control. This paper describes two selection mechanisms into QPSO to improve the search ability of QPSO. One is the QPSO with tournament selection (QPSO-TS) and the other is the QPSO with roulette-wheel selection (QPSO-RS). While the centre of position distribution of each particle in QPSO is determined by global best position and personal best position, in the QPSO with selection operation, the global best position is substituted by a candidate solution through selection. The QPSO with selection operation also maintains the mean best position of the swarm as in the previous QPSO to make the swarm more efficient in global search. The experiment results on benchmark functions show that both QPSO-RS and QPSO-TS have better performance and stronger global search ability than QPSO and standard PSO.