摘要
蚁群算法的参数设置一直是依靠经验和实验来确定,造成实验工作量大且难以得到最优的参数组合,影响了算法的使用。从基本蚂蚁算法出发,结合实验结果,讨论了α、β及ρ的变化对实验结果的影响,提出了相应的参数改进方案。并将经此方案修正的蚂蚁算法与基本蚂蚁算法同时运用于经典函数优化问题中,对仿真结果进行了对比。
The enactment of the parameters of an ant system is determined by experience and experiment.This leads to heavy work load and makes the optimal combination of the parameters difficult to obtain.On the basis of the ant algorithm and the re sult of the experiment,the effect by changing the parameters of α、β、ρ is discussed,and an improved scheme is proposed.Then both of the improved scheme and the ant algorithm are applied to the function optimization problem,and a comparison is made in the simulation.
出处
《计算机工程与应用》
CSCD
北大核心
2008年第17期53-55,共3页
Computer Engineering and Applications
基金
甘肃省自然科学基金(the Natural Science Foundation of Gansu Province of China under Grant No.3ZS024- B25- 034)
关键词
蚁群算法
函数优化
组合优化
参数设置
ant colony algorithm
function optimization
combinatorial optimization
optimum configurations
