Publicação
An Heterogeneous Particle Swarm Optimizer With Predator and Scout Particles
| Resumo: | Wepresentanewheterogeneousparticleswarmoptimization algorithm, called scouting predator-prey optimizer. The algorithm uses the interactions of the swarm with a predator particle to control the bal- ance between exploration and exploitation. Scout particles are proposed as a straightforward way of introducing new exploratory behaviors into the swarm. These can range from new heuristics that globally improve the algorithm to modifications based on problem specific knowledge. The scouting predator-prey optimizer is compared with several variations of both particle swarm and differential evolution algorithms, using a a set of benchmark functions selected to present the algorithms with different obstacles and difficulties. The experimental results suggest the new opti- mizer can outperform the other approaches over most of the benchmark problems. |
|---|---|
| Autores principais: | Silva, Arlindo |
| Outros Autores: | Neves, Ana; Gonçalves, Teresa |
| Assunto: | swarm intelligence particle swarm optimization heterogeneous particle swarms |
| Ano: | 2013 |
| País: | Portugal |
| Tipo de documento: | artigo |
| Tipo de acesso: | acesso restrito |
| Instituição associada: | Universidade de Évora |
| Idioma: | inglês |
| Origem: | Repositório Científico da Universidade de Évora |
| Resumo: | Wepresentanewheterogeneousparticleswarmoptimization algorithm, called scouting predator-prey optimizer. The algorithm uses the interactions of the swarm with a predator particle to control the bal- ance between exploration and exploitation. Scout particles are proposed as a straightforward way of introducing new exploratory behaviors into the swarm. These can range from new heuristics that globally improve the algorithm to modifications based on problem specific knowledge. The scouting predator-prey optimizer is compared with several variations of both particle swarm and differential evolution algorithms, using a a set of benchmark functions selected to present the algorithms with different obstacles and difficulties. The experimental results suggest the new opti- mizer can outperform the other approaches over most of the benchmark problems. |
|---|
Atividades financiadas
Não foram encontrados projetos financiados.