Skip to main navigation Skip to search Skip to main content

Migration & competition-based particle swarm optimization for parameter estimation

  • Ziwu Ren*
  • , Zhenhua Wang
  • , Lining Sun
  • *Corresponding author for this work
  • Soochow University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Enlightened by some knowledge of ecology and swarm competition, an improved multigrouped particle swarm optimization based on migration and competition, namely PSOMC, is proposed for parameters estimation of non-linear systems. The PSOMC is not concerned with the evolution of a single population, but instead is concerned with the evolution of multiple parallel swarms; moreover it incorporates some concepts, such as reintroduction, swarm competition, adjustment of swarm size, migration of particles between the swarm, and recycling, to enhance the global exploration ability and the local exploitation capability. Numerical simulations of two benchmark functions are used to test the performance of PSOMC. Furthermore, simulation on three different kinds of models is given to illustrate the effectiveness and efficiency of the proposed parameters estimation scheme.

Original languageEnglish
Title of host publicationWCICA 2012 - Proceedings of the 10th World Congress on Intelligent Control and Automation
Pages590-595
Number of pages6
DOIs
StatePublished - 2012
Externally publishedYes
Event10th World Congress on Intelligent Control and Automation, WCICA 2012 - Beijing, China
Duration: 6 Jul 20128 Jul 2012

Publication series

NameProceedings of the World Congress on Intelligent Control and Automation (WCICA)

Conference

Conference10th World Congress on Intelligent Control and Automation, WCICA 2012
Country/TerritoryChina
CityBeijing
Period6/07/128/07/12

Keywords

  • Particle swarm optimization
  • competition
  • migration
  • nonlinear model
  • parameter estimation

Fingerprint

Dive into the research topics of 'Migration & competition-based particle swarm optimization for parameter estimation'. Together they form a unique fingerprint.

Cite this