A Multi-Swarm Cooperative Perturbed Particle Swarm Optimization

Abstract:

Article Preview

Combined with a variety of ideas a Multi-swarm cooperative Perturbed Particle Swarm Optimization algorithm (MpPSO) is presented to improve the performance and to reduce the premature convergence of PSO. This algorithm includes the idea of multiple swarms to improve the evolution efficiency by information sharing between populations to avoid falling into local optimum caused by single population. It also includes the idea of perturbing the swarms beside the global best solution, which can escape from local optimum. Experiments show that the proposed algorithm MpPSO has better performance, better convergence and stability when comparing with the traditional and the recently improved particle swarm optimization.

Info:

Periodical:

Advanced Materials Research (Volumes 225-226)

Edited by:

Helen Zhang, Gang Shen and David Jin

Pages:

619-622

DOI:

10.4028/www.scientific.net/AMR.225-226.619

Citation:

X. J. Yang et al., "A Multi-Swarm Cooperative Perturbed Particle Swarm Optimization", Advanced Materials Research, Vols. 225-226, pp. 619-622, 2011

Online since:

April 2011

Export:

Price:

$35.00

In order to see related information, you need to Login.

In order to see related information, you need to Login.