Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
9651026 | Information Sciences | 2005 | 21 Pages |
Abstract
The article presents a novel population-based optimisation method, called Free Search (FS). Essential peculiarities of the new method are introduced. The aim of the study is to identify how robust is Free Search. Explored and compared are four different population-based optimisation methods, namely Genetic Algorithm (in real coded BLX-α modification), Particle Swarm Optimisation, Differential Evolution and Free Search. They are applied to five non-linear, heterogeneous, numerical, optimisation problems. The achieved results suggest that Free Search has stable robust behaviour on explored tests; FS can cope with heterogeneous optimisation problems; FS is applicable to unknown (black-box) real-world optimisation tasks.
Keywords
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
Kalin Penev, Guy Littlefair,