Evolutionary Optimization in Dynamic Environments
Evolutionary Optimization in Dynamic Environments
Unsupervised fuzzy learning and cluster seeking
Intelligent Data Analysis
A Generalized Approach to Construct Benchmark Problems for Dynamic Optimization
SEAL '08 Proceedings of the 7th International Conference on Simulated Evolution and Learning
| Hi-index | 0.00 |
Dynamic Optimization Problems (DOPs) are a defiance for Genetic Algorithms. In DOPs, a varied number of optima, either local or global, that dynamically change their position and shape in the search space. When applied to DOPs, the standard Genetic Algorithms (SGAs) loose the population diversity. This diversity is necessary for locating multiple optima and for adapting to changes in them. Many researchers have proposed algorithms to enhance the performance of GAs in DOPs. This paper is motivated for applying multimodal optimization technique with a number of remedies to address dynamic optimization problems. First, we use GAs with Dynamic Niche Sharing (GADNS) to maintain diversity in population and to find multiple optima. Second, we perform with an unsupervised fuzzy clustering algorithms to track multiple optima and to overcome some limitations of GADNS. Third, we use a fuzzy system to adjust the population diversity with the mutation and crossover rates. A novel genetic operator inspired by bacterial conjugation is used to improve GAs. A modified tournament selection is used to control the selection pressure. The effectiveness of our approach is demonstrated by using Generalized dynamic benchmark generator (GDBG).