一种基因与蚁群的融合算法研究  

A new hybrid algorithm of gene algorithm and ant algorithm

作　　者：林振荣[1] 

机构地区：[1]南昌大学信息工程学院计算机系,南昌330031

出　　处：《微计算机信息》2007年第36期176-177,200,共3页Control & Automation

基　　金：国家火炬计划项目(2005EB010944)资助

摘　　要：蚁群算法具有分布式并行搜索能力,通过信息素的积累和更新收敛于最优路径上,但初期信息素匮乏,收敛较慢。提出一种基因算法与蚁群算法融合的算法,将基因算法加入蚁群算法的每一次迭代中,利用基因算法快速收敛的优点,来加快蚁群系统的收敛速度;且基因算法中的变异机制,有利于提高蚁群算法跳出局部最优的能力。优势互补,实验结果表明该基因蚁群融合算法在寻优能力和收敛速度上都比基因算法和蚁群算法有较大的提高。Ant algorithm has the ability of distributed searching and parallel processing, converges on the optimization path through information pheromone accumulation and renewal. The convergence speed is slow, because there is little information pheromone on the early path： A new hybrid algorithm combining gene algorithm with ant algorithm is proposed, adds gene algorithm to ant algorithm every step, which makes use of gene advantage of quick convergence and the ability of mutation mechanism. It deeply develops advantage of the two algorithms, and experimental results show that the method has high convergence speed, good global search ability, which are better than gene algorithm and ant algorithm.

关 键 词：基因算法 蚁群算法 优化 

分 类 号：TN918[电子电信—通信与信息系统]