作　　者： ; ; ;

机构地区： 华南理工大学计算机科学与工程学院

出　　处： 《哈尔滨工程大学学报》 2006年第B07期518-522,共5页

摘　　要： 蚁群算法是一种新的进化算法，其基本思想是模拟蚂蚁的合作行为．蚁群算法已成功地应用于许多优化问题，成为求解组合优化问题的新的进化算法．最新研究表明蚁群算法是一种基于群体的强鲁棒性的进化算法．但是，蚁群算法也有收敛速度慢，容易陷入局部最优的缺点．为了克服这些缺点，吸取微粒群算法的优点，提出了一种改进的蚁群算法．实验结果表明改进算法是有效的，与标准的蚁群算法相比，算法性能得到了明显改善． Artificial ant colony algorithm （ACA） is new in the evolution computing. The basic idea is to imitate the cooperative behavior of ant colonies. ACA has achieved widespread success in solving different optimization problems, especially in solving combinatorial optimization problems. The primary study shows it is a better robust algorithm based on population, but it has some shortcomings such as its slow computing speed, and it is easy to fall in local peak in large scale problem. To overcome these deficiencies, an improved ant colony algorithm is designed through abstracting the advantages of particle swarm optimization （PSO）. The results of the experiment suggest that the improved algorithm is effective. Results are very promising compared to the corresponding results of the standard ant colony algorithm, indicating the superiority of the new scheme.

关 键 词： 蚁群算法 问题 信息素 微粒群算法

领　　域： [自动化与计算机技术] [自动化与计算机技术]