Segment message exchange based Differential Evolution Algorithm
| Autor: | Tse Su, 蘇哲 |
|---|---|
| Rok vydání: | 2014 |
| Druh dokumentu: | 學位論文 ; thesis |
| Popis: | 102 In general, different type of basic mutation strategies differential evolution will affect evolutionary directions directly. However, it cannot be avoided that all the basic mutation strategies may drive vectors form fall into local optimal solutions. In order to overcome this weakness of differential evolution, in this paper, the segment message exchange based differential evolution algorithm, which is with featuring sustained convergence, is proposed for solving single-objective optimization problems. In order to address the weaknesses of differential evolution, in this study, the mutation and crossover strategies of the basic-type differential evolution were modified to prevent premature convergence of the algorithm and from fall into local optimal solution. Furthermore, the dissolution mechanism is proposed. After several iterations, the solutions may become very similar. The dissolution mechanism will be activated to regenerate all the vectors except the best vectors will be retained. It will force algorithm to re-search the solution space. In the experiments, the CEC2005 test functions were adopted to test the proposed method and compare it with related methods which proposed in recent years. From the results, it can be observed that the proposed performs better in most test functions than other DE approaches, and exhibit signification improvement in solving specific problems. |
| Databáze: | Networked Digital Library of Theses & Dissertations |
| Externí odkaz: |
|