求解函数优化问题的混合连续优化算法

Hybridized continuous ant colony optimization algorithm for solving function optimization problems

用蚁群算法进行函数优化时,存在收敛速度慢且易于陷入局部最优解的问题。针对这一现状,提出了一种微粒群和蚂蚁算法相结合的混合连续优化算法,该算法引入微粒群优化操作进行全局搜索牵引,采用网格法进行细密度的蚂蚁局部搜索,从而能很好地应用于求解连续对象优化问题。对若干典型复杂连续函数的实验测试结果表明,该混合算法跳出局部最优解的能力较强,能较快地收敛到全局最优解,并能适于高维空间的优化问题。与最新的有关研究成果相比,该算法不仅寻优精度高,而且收敛速度大幅提高,效果十分令人满意。

Such problems as slow convergence and easy falling to the local optimization problems tend to exist in the continuous optimization by means of ant colony algorithm. In order to deal with these problems,this paper presented a new ant colony algorithm which hybridized particle swarm optimization（ PSO） algorithm with ant colony optimization（ ACO） algorithm. It used PSO for global traction,and used grid-based ant colony for precise local search. As a result,the algorithm could well be applied in solving continuous optimization problems. The experimental results obtained on some typical benchmark problems show that the proposed algorithm can not only jump out of the local optimal solution easily,and achieve rapid convergence speed in the global optimal,but also is suitable for the high-dimensional space optimization problem. Compared with the recent relevant research outcome,the algorithm proved satisfying,as high accuracy and quick convergence can be achieved.