Interval search with quadratic interpolation and stable deviation quantum-behaved particle swarm optimization (IQS-QPSO)

Abstract

In this article, in order to enhance the rate of convergence and scattering of particles at the same time, simple techniques are introduced. These techniques include: (1) Using the interval search to select a new particle candidate, (2) Replacement of three candidate particles instead to worst the particles in the population, (3) Using the best result of learning coefficients, (4) using a simple method to control the convergence of the algorithm in a high number of repetitions. In this article, the performance of Quantum-Behaved Particle Swarm Optimization (QPSO) algorithm has been upgraded with using the interval search method. The proposed method of interval search of quantum-behaved particle swarm optimization algorithm has achieved better results than in the past with the use of quadratic interpolation recombination operator and stable deviation and interval search. Moreover, the results of the proposed algorithm of Interval Search with Quadratic Interpolation and Stable Deviation Quantum-Behaved Particle Swarm Optimization (IQS-QPSO) is compared with the other former algorithms such as Quantum-Behaved Particle Swarm Optimization (QPSO), Quadratic Interpolation Quantum-Behaved Particle Swarm Optimization (Q-QPSO) and Stable Deviation Quantum-Behaved Particle Swarm Optimization (SD-QPSO). Then the performance improvement is reported. In order to compare the results of each algorithm, five famous functions are used and consequently the results are reported separately for each function.