基于网格划分策略的改进人工鱼群算法  

An Improved Artificial Fish-Swarm Algorithm Based on Gridding Method

作　　者：黄光球[1] 王西邓[1] 刘冠[1] 

机构地区：[1]西安建筑科技大学管理学院,陕西西安710055

出　　处：《微电子学与计算机》2007年第7期83-86,90,共5页Microelectronics & Computer

基　　金：陕西省教育厅专项基金项目(06JK258)

摘　　要：人工鱼群算法是一种新型的随机搜索优化算法,初步研究表明该算法具有许多优良的性质。通过引入网格划分策略和禁忌搜索算法,对基本人工鱼群算法进行了改进,减少了迂回搜索的无用计算,同时也使人工鱼可以在解空间内进行更为全面的搜索,提高了搜索效率,加快了系统满意解域的确定;通过对变量空间进行网格划分,提供了获取系统最优解的方法,而且加强了对鱼群公告板信息的使用。实验表明,与基本人工鱼群算法相比,该方法具有明显的优越性。Artificial fish-swarm algorithm is a new random search optimization algorithm. Preliminary study shows that it has many promising features. Based on girding method and tabu search algorithm, an improved artificial fish-swarm algorithm is presented. In the method a large number of unused circuitous searches are reduced, a more complete search within solution space is obtained for artificial fishes so that a high search efficiency is arrived at and determination of satisfactory solution domain is quickened; through gridding of variables space, a method to obtain the optimum solution is provided and use of information hoard of artificial fish-swarm is strengthened. Results of experiments show that there is an obvious advantage for this improved method when compared with the basic artificial fish-swarm algorithm.

关 键 词：网格划分策略 禁忌搜索 人工鱼群算法 优化 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]