Boundary constraint handling techniques for particle swarm optimization in high dimensional problem spaces

Loading...
Thumbnail Image

Authors

Oldewage, E.T. (Elre)
Engelbrecht, Andries P.
Cleghorn, Christopher Wesley

Journal Title

Journal ISSN

Volume Title

Publisher

Springer

Abstract

This paper investigates the use of boundary constraint handling mechanisms to prevent unwanted particle roaming behaviour in high dimensional spaces. The paper tests a range of strategies on a benchmark for large scale optimization. The empirical analysis shows that the hyperbolic strategy, which scales down a particle’s velocity as it approaches the boundary, performs statistically significantly better than the other methods considered in terms of the best objective function value achieved. The hyperbolic strategy directly addresses the velocity explosion, thereby preventing unwanted roaming.

Description

Keywords

Particle swarm optimization (PSO), Swarm intelligence, A-particles, Boundary constraints, Empirical analysis, High dimensional spaces, High-dimensional problems, Large-scale optimization, Objective function values, Paper tests, Hyperbolic functions

Sustainable Development Goals

Citation

Oldewage E.T., Engelbrecht A.P., Cleghorn C.W. (2018) Boundary Constraint Handling Techniques for Particle Swarm Optimization in High Dimensional Problem Spaces. In: Dorigo M., Birattari M., Blum C., Christensen A., Reina A., Trianni V. (eds) Swarm Intelligence. ANTS 2018. Lecture Notes in Computer Science, vol 11172. Springer, Cham.