2009 | OriginalPaper | Buchkapitel
Continuous Constrained Optimization with Dynamic Tolerance Using the COPSO Algorithm
verfasst von : Angel E. Muñoz Zavala, Arturo Hernández Aguirre, Enrique R. Villa Diharce
Erschienen in: Constraint-Handling in Evolutionary Optimization
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
This work introduces a hybrid PSO algorithm which includes perturbation operators to keep population diversity. A new neighborhood structure for Particle Swarm Optimization called Singly-Linked Ring is implemented. The approach proposes a neighborhood similar to the ring structure, but which has an innovative neighbors selection. The objective is to avoid the premature convergence into local optimum. A special technique to handle equality constraints with low side effects on the diversity is the main feature of this contribution. Two perturbation operators are used to improve the exploration, applying the modification only in the particle best population.We show through a number of experiments how, by keeping the selection pressure on a decreasing fraction of the population, COPSO can consistently solve a benchmark of constrained optimization problems.