An Improved Particle Swarm Optimization Algorithm Mimicking Territorial Dispute Between Groups for Multimodal Function Optimization Problems

• Published in: IEEE transactions on magnetics Vol. 44; no. 6; pp. 1046 - 1049
• Main Authors: SEO, Jang-Ho, IM, Chang-Hwan, KWAK, Sang-Yeop, LEE, Cheol-Gyun, JUNG, Hyun-Kyo
• Format: Journal Article Conference Proceeding
• Language: English
• Published: New York, NY IEEE 01.06.2008; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithm design and analysis; Algorithms; Biomedical engineering; Birds; Computer science; Convergence; Cross-disciplinary physics: materials science; rheology; Design optimization; Ecosystems; Electromagnetic optimization problems; Exact sciences and technology; Magnetism; Materials science; multi-grouped particle swarm optimization (MGPSO); multimodal function optimization; Optimization; Other topics in materials science; Particle swarm optimization; particle swarm optimization (PSO); Physics; Robustness; Testing; Electromagnetic optimization problems; multimodal function optimization; particle swarm optimization (PSO); multi-grouped particle swarm optimization (MGPSO); Magnetic properties
• ISSN: 0018-9464; 1941-0069
• DOI: 10.1109/TMAG.2007.914855

In the present paper, an improved particle swarm optimization (PSO) algorithm for multimodal function optimization is proposed. The new algorithm, named auto-tuning multigrouped PSO (AT-MGPSO) algorithm mimics natural phenomena in ecosystem such as territorial dispute between different group members and immigration of weak groups, resulting in automatic determination of the size of each group's territory and robust convergence. The usefulness of the proposed algorithm is verified by the application to a specially designed test function and a practical electromagnetic optimization problem.