| 4,377 | 593 | 265 |
| 下载次数 | 被引频次 | 阅读次数 |
蚁群算法是一种模拟进化算法,初步的研究表明该算法具有许多优良的性质.本文介绍了蚁群算法基本模型AS(AntSystem)的原理、特点、构成和实现方法,对基本蚁群算法参数的合理选取进行了实验分析,给出了算法参数选取的基本原则,有利于蚁群算法在优化问题中的推广和应用.
Abstract：The ant colony algorithm is a novel simulated evolutionary algorithm which shows many good properties. This paper presents the principle, the characteristics, the construction and realization method about the basic model AS (Ant System) of the ant colony algorithm. Experimental analyses are carried out on the reasonable selection on the parameters of this algorithm, and basic principles for the parameter selection are provided. The results from this paper are beneficial to the application and development of the ant colony algorithm in optimization problems.
[1] BartoAG,SuttonRS,BrowerPS.Associativesearchnetwork:Areinforcementlearningassociativememory[J].BiologicalCybern,1981,40(2):201～211.
[2] ColoniA,DorigoM,ManiezzoV.Antsystem:Optimizationbyacolonyofcooperatingagent[J].IEEETransonSystems,ManandCybernetics PartB:Cybernetics.1996,26(1):29～41.
[3] DorigoM,GambardellaLM.Antcolonysystem:AcooperativelearningapproachtothetavellingsalesmanProblem[J].IEEETransonEvolutionaryComputation.1996,1(1):53～66.
[4] 马 良.来自昆虫世界的寻优策略———蚁群算法[J].自然杂志,1999,21(3):161～163.
[5] 张纪会,高齐圣,徐心和.自适应蚁群算法[J].控制理论与应用.2000,17(1):1～8.
基本信息:
DOI：10.13774/j.cnki.kjtb.2003.05.008
中图分类号:TP301.6
引用信息:
[1]詹士昌,徐婕,吴俊.蚁群算法中有关算法参数的最优选择[J].科技通报,2003(05):381-386.DOI:10.13774/j.cnki.kjtb.2003.05.008.
基金信息:
杭州师范学院科研基金资助重点项目(2001XA612)