基于云群的高维差分进化算法及其在网络安全态势预测上的应用  

High dimensional differential evolutionary algorithm based on cloud population for network security prediction

作　　者：胡冠宇[1] 乔佩利[1] 

机构地区：[1]哈尔滨理工大学计算机科学与技术学院,哈尔滨150080

出　　处：《吉林大学学报（工学版）》2016年第2期568-577,共10页Journal of Jilin University:Engineering and Technology Edition

基　　金：国家自然科学基金项目(61103149);黑龙江省自然科学基金项目(QC2013C060)

摘　　要：提出了一种基于云群的高维差分进化算法(CPDE),并将其应用在网络安全态势预测领域。该算法所提出的云群和分布链概念增加了种群的多样性。算法中的入侵算子将获胜个体的分布植入给其他个体,使得在进化的过程中,个体的形态呈现多样性。协作算子在个体之间引入了合作机制并执行差分操作。局部搜索算子增加了算法的搜索精度。实验结果显示CPDE是一个有效的高维进化算法,它在优化网络安全态势预测模型中具有一定的优势。A novel differential evolutionary algorithm based on could population（CPDE）is proposed to solve the network security situation prediction.The proposed concepts of cloud population and the distribution chain promote the diversity of the population.In this algorithm,first,the intrusion operator is employed to introduce the competition among the cloud populations,where the winners will implant their distribution into other cloud individuals.Then,cooperative operator is used to introduce the collaboration among the cloud individuals and perform the differential operation.Finally,the accuracy of the algorithm is improved using the local search operator.Experiment results show that the proposed CPDE is an efficient high-dimensional evolutionary algorithm and possesses certain advantages in optimizing the prediction model of the network security.

关 键 词：计算机应用技术 差分进化算法 云模型 云群 分布链 网络安全态势预测 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]