Containing particles inside niches when optimizing multimodal functions

Traditionally particle swarm optimization was employed to locate a single optimal solution in a search space. The strategy can be adapted in niching algorithms to find multiple optimal solutions in a problem domain. Initially good candidate solutions must be found to serve as nuclei around which subswarms can be optimized to converge on multiple optimal solutions. Several strategies have been developed to address the problem. Algorithms to accomplish this should not depend on prior knowledge of the objective function to find starting points and estimate the niche boundaries.In previous work the authors introduced a vector-based approach to identify and demarcate the initial niches. Niches were originally optimized sequentially and later in parallel. A critical objective entailed the minimization of tunable parameters and problem dependence. This paper presents an enhanced parallel vector-based particle swarm optimizer where niches are identified using vector operations and subswarms optimized in parallel without using a niche radius.

[1]  Michael N. Vrahatis,et al.  Modification of the Particle Swarm Optimizer for Locating All the Global Minima , 2001 .

[2]  Ralph R. Martin,et al.  A Sequential Niche Technique for Multimodal Function Optimization , 1993, Evolutionary Computation.

[3]  Frans van den Bergh,et al.  An analysis of particle swarm optimizers , 2002 .

[4]  Andries P. Engelbrecht,et al.  Computational Intelligence: An Introduction , 2002 .

[5]  Andries P. Engelbrecht,et al.  A Parallel Vector-Based Particle Swarm Optimizer , 2005 .

[6]  Yue Shi,et al.  A modified particle swarm optimizer , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[7]  K. Parsopoulos,et al.  Stretching technique for obtaining global minimizers through Particle Swarm Optimization , 2001 .

[8]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[9]  James Kennedy,et al.  Small worlds and mega-minds: effects of neighborhood topology on particle swarm performance , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[10]  A. Engelbrecht,et al.  Using vector operations to identify niches for particle swarm optimization , 2004, IEEE Conference on Cybernetics and Intelligent Systems, 2004..