摘要
在深入研究基本的万有引力搜索算法基础上,将进化计算过程中的高斯变异引入引力搜索算法的位置更新中,增强引力搜索算法跳出局部最优解的能力。经典的测试函数验证了该算法的性能,并与基本的万有引力搜索算法及基于权值的引力搜索算法作比较,结果表明基于高斯变异的引力搜索算法更容易跳出局部最优,在求解函数的优化问题中表现出更好的性能。
In this paper,we study the underlying gravitational search algorithm,and introduce the Gassian mutation of the evolutionary computation process into the position update of the gravitational search algorithm,which can enhance the ability to jump out of the local optima. The performance of the algorithm is verifyied by the classical test functions.The results show that the search algorithm based on the Gaussian mutation gravitation is more likely to jump out of local optima compared with the underlying gravitational search algorithm and the search algorithm based on the weight gravitation,and performs better in solving the problem of optimized functions.
出处
《江南大学学报（自然科学版）》
CAS
2015年第5期596-600,共5页
Joural of Jiangnan University (Natural Science Edition)
关键词
引力搜索算法
局部搜索
高斯变异
收敛速度
gravitational search algorithm
local search
Gaussian mutation
conver gence speed
