<abstract xmlns="http://www.w3.org/1999/xhtml"><p>Particle Swarm Optimization is an evolutionary optimization algorithm, largely studied during the years: analysis of convergence, determination of the optimal coefficients, hybridization of the original algorithm and also the determination of the best relationship structure between the swarm elements (topology) have been investigated largely. Unfortunately, all these studies have been produced separately, and the same coefficients, derived for the original topology of the algorithm, have been always applied. The intent of this paper is to identify the best set of coefficients for different topological structures. A large suite of objective functions are considered and the best compromise coefficients are identified for each topology. Results are finally compared on the base of a practical ship design application.</p></abstract>

Particle Swarm Optimization is an evolutionary optimization algorithm, largely studied during the years: analysis of convergence, determination of the optimal coefficients, hybridization of the original algorithm and also the determination of the best relationship structure between the swarm elements (topology) have been investigated largely. Unfortunately, all these studies have been produced separately, and the same coefficients, derived for the original topology of the algorithm, have been always applied. The intent of this paper is to identify the best set of coefficients for different topological structures. A large suite of objective functions are considered and the best compromise coefficients are identified for each topology. Results are finally compared on the base of a practical ship design application.

Effect of parameter selection on different topological structures for Particle Swarm Optimization algorithm

CNR-IAC – National Research Council - Istituto per le Applicazioni del Calcolo “Mauro Picone”

Communications in Applied and Industrial Mathematics

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Particle Swarm Optimization is an evolutionary optimization algorithm, largely studied during the years: analysis of convergence, determination of the optimal...

Effect of parameter selection on different topological structures for Particle Swarm Optimization algorithm

Data publikacji: 18 lis 2019

Zakres stron: 199 - 207

Otrzymano: 05 mar 2019

Przyjęty: 21 paź 2019

DOI: https://doi.org/10.2478/caim-2019-0021

Słowa kluczowe
Optimization, Heuristic methods, Evolutionary computation, Particle Swarm Optimization

© 2019 Daniele Peri, published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Effect of parameter selection on different topological structures for Particle Swarm Optimization algorithm

Data publikacji: 18 lis 2019

Zakres stron: 199 - 207

Otrzymano: 05 mar 2019

Przyjęty: 21 paź 2019

DOI: https://doi.org/10.2478/caim-2019-0021

Słowa kluczoweOptimization, Heuristic methods, Evolutionary computation, Particle Swarm Optimization

© 2019 Daniele Peri, published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Słowa kluczowe
Optimization, Heuristic methods, Evolutionary computation, Particle Swarm Optimization