Adaptive Zooming Genetic Algorithm for Continuous Optimisation Problems
Authors: | Li Kang, Queen's University Belfast, United Kingdom Peng Jian-xun, Queen's University Belfast, United Kingdom Thompson Steve, Queen's University Belfast, United Kingdom |
---|
Topic: | 3.2 Cognition and Control ( AI, Fuzzy, Neuro, Evolut.Comp.) |
---|
Session: | Genetic and Evolutionary Algorithms |
---|
Keywords: | Genetic algorithms, optimisation, convergence, adaptation, robustness |
---|
Abstract
This paper proposes an adaptive zooming genetic algorithm (AZGA) for continuous optimisation problems. Other than gradually reducing the search space with a fixed reduction rate during the evolution process, the upper and the lower boundaries for each variable in the objective function are dynamically adjusted. The search space adjustment is based on the distribution information of the variables in the whole population. This technique is evaluated on a suite of benchmark test functions, and the results show its superiority to existing techniques in terms of convergence speed and robustness.