| 摘要: |
| 提出了一种种群规模自适应动态控制策略,实现了种群规模根据进化过程自适应的动态变化.该策略的实现不依赖于算法进化操作的具体步骤,因而适用于各种基于种群优化的自然计算方法.首先给出了动态控制策略的框架;然后,在此框架下,充分利用动态种群规模反馈的有用信息,提出了基于Logistic 模型的增加/删除数目自适应变化的方法,设计了自适应地兼顾有效性和多样性的增加算子和基于多样性的删除算子.将该策略应用到两种不同的自然计算方法中,采用经典测试函数和新型CEC05 测试函数验证其性能.实验结果均表明,结合了所提出的种群规模自适应动态控制策略的新算法,比原算法在求解精度和收敛速度上均有明显的提升. |
| 关键词: 自然计算 种群规模 动态控制 Logistic 模型 数值优化 |
| DOI：10.3724/SP.J.1001.2012.04151 |
| 分类号: |
| 基金项目:国家自然科学基金(60872135, 60803098, 61001202, 61003199); 陕西省“13115”科技创新工程重大科技专项(2008ZDKG-37); 高等学校学科创新引智计划(B07048); 国家教育部博士点基金(200807010003, 20090203120016, 20100203120008); 国家部委科技项目(9140A07011810DZ0107, 9140A07021010DZ0131); 中央高校基本科研业务费专项资金(K50510020001) |
|
| Nature Computation with Self-Adaptive Dynamic Control Strategy of Population Size |
|
WANG Rong-Fang1, JIAO Li-Cheng1, LIU Fang1,2, YANG Shu-Yuan1
|
|
1.Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education (Xidian University), Xi’an 710071, China;2.School of Computer Science and Technology, Xidian University, Xi’an 710071, China
|
| Abstract: |
| A new self-adaptive dynamic control strategy of population size is proposed. This strategy can be easily combined with various nature computation methods because its implementation is independent of the evolutionary operation details. The framework of the strategy is first given. Based on the framework, the study proposes a method which can vary the number of increase/decrease on the basis of the logistic model. The study also designs an increase operator giving consideration to the effectiveness and diversity adaptively, as well as a decrease operator with the diversity. The strategy is applied to two different nature computation methods. Experimental evaluation is conducted on both a set of standard test functions and a new set of benchmark functions CEC05. The results show that the new algorithms with proposed strategy outperform the original algorithms on both the precision and convergence rate. |
| Key words: nature computation population size dynamic control Logistic model numerical optimization |
