Adaptive direction information in differential evolution for numerical optimization |
| |
Authors: | Yiqiao Cai Jiahai Wang Yonghong Chen Tian Wang Hui Tian Wei Luo |
| |
Affiliation: | 1.College of Computer Science and Technology,Huaqiao University,Xiamen,China;2.Department of Computer Science,Sun Yat-sen University,Guangzhou,China |
| |
Abstract: | Differential evolution (DE) is a powerful evolutionary algorithm (EA) for numerical optimization. It has been successfully used in various scientific and engineering fields. In most of the DE algorithms, the neighborhood and direction information are not fully and simultaneously exploited to guide the search. Most recently, to make full use of these information, a DE framework with neighborhood and direction information (NDi-DE) was proposed. It was experimentally demonstrated that NDi-DE was effective for most of the DE algorithms. However, the performance of NDi-DE heavily depends on the selection of direction information. To alleviate this drawback and improve the performance of NDi-DE, the adaptive operator selection (AOS) mechanism is introduced into NDi-DE to adaptively select the direction information for the specific DE mutation strategy. Therefore, a new DE framework, adaptive direction information based NDi-DE (aNDi-DE), is proposed in this study. With AOS, the good balance between exploration and exploitation of aNDi-DE can be dynamically achieved. In order to evaluate the effectiveness of aNDi-DE, the proposed framework is applied to the original DE algorithms, as well as several advanced DE variants. Experimental results show that aNDi-DE is able to adaptively select the most suitable type of direction information for the specific DE mutation strategy during the evolutionary process. The efficiency and robustness of aNDi-DE are also confirmed by comparing with NDi-DE. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|