Adaptive Differential Evolution Algorithm with High Diversity Population
| Autor: | Huang-Lyu Wu, 吳皇履 |
|---|---|
| Rok vydání: | 2014 |
| Druh dokumentu: | 學位論文 ; thesis |
| Popis: | 102 This paper proposed an adaptive differential evolution algorithm with high diversity population (ADE-HP). The proposed method can increase diversity of population and increase vectors’ searching ability for solving single-objective numerical optimization problems. In order to increase diversity of population in original DE, several mechanisms are proposed. First, Elitist mechanism can avoid vectors are guided to the same position (global best particle) and can prevent vectors form fall into local optimum even early convergence. Second, Real rand mechanism can give higher ability to jump out from local optimum and provide varied information to help particles toward to potential unsearched solution space for solution exploration. Finally, in order to increase vectors’ explore probability, the partial crossover mechanism is proposed. 25 test functions of CEC 2005 were adopted for experiments through a reasonable average and fitness evaluations. From the results, it can be observed that the proposed method can efficiently find better solutions than recent DE works for solving optimization problems. |
| Databáze: | Networked Digital Library of Theses & Dissertations |
| Externí odkaz: |
|