基于高斯采样和随机采样聚类的差分演化算法  

A Clustering Differential Evolution Algorithm Based on Random Sampling and Gaussian Sampling

作　　者：程钢[1] 刘罡[1] 胡延忠[1] 

机构地区：[1]湖北工业大学计算机学院,湖北武汉430068

出　　处：《湖北工业大学学报》2016年第2期45-48,110,共5页Journal of Hubei University of Technology

基　　金：国家自然科学基金项目(61300127)

摘　　要：基于中心采样的概念,提出随机采样方法。研究差分演化算法,提出基于高斯采样和随机采样的聚类差分演化算法。通过实验,论证了高斯采样和随机采样显著的加快收敛速度、提升算法的求解能力,表明该算法对复杂的全局优化问题有很好地求解能力,比经典差分演化算法具有更好的求解性能。Based on the concept of center-based sampling,the paper proposed a method of random sampling.It studied the Differential Evolution,proposing the clustering differential evolution algorithm based on random sampling and Gaussian sampling（GRCDE）.Experiment results indicate the Gaussian sampling and the random sampling remarkably accelerate the convergence rate and improves exploitation ability of DE.It shows that GRCDE has a better solving ability and our proposed GRCDE performs better than some DE variants.

关 键 词：差分演化算法 全局优化 随机采样 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]