基于禁忌遗传算法和支持向量机的网络安全态势预测  

Prediction of Network Security Situation Based on Tabu Gene Algorithm and Support Vector Machine

作　　者：邵伯乐[1] 李洁 SHAO Bo-le;LI Jie(Bozhou Vocational and Technical College,Bozhou 236800,China)

机构地区：[1]亳州职业技术学院,安徽亳州236800

出　　处：《宜春学院学报》2018年第12期56-58,共3页Journal of Yichun University

基　　金：安徽省教育厅自然科学重点基金项目"大数据环境下中药材销售数据处理方法与市场预测研究与应用"(KJ2018A0887);亳州职业技术学院院级课题(BYK1711)

摘　　要：针对网络安全态势预测的现有的方法预测精度不高和预测时间过长的问题,提出了一种基于禁忌遗传算法和支持向量机的在线网络安全态势预测方法。首先,建立了基于支持向量机的网络安全态势模型;其次,定义了基于禁忌遗传算法实现对支持向量机的参数优化的具体算法,实现对支持向量机决策模型的参数优化。为了验证所提方法的优越性,采用某虚拟网络的实时数据作为仿真环境,并将所提模型与其他方法进行比较,仿真实验证明了文中方法能有效地进行预测,在仿真时间几乎相近的情况下,具有较高的评估准确率。Aiming to the problems such as the low accuracy of the prediction method and long prediction time at the traditional network security situation method,a network security prediction method based on Tabu gene algorhm and Support vector machine is proposed.Firstly,the network security situation model based on Support vector machine is established.Then the specific algorithm based on Tabu algorithm for optimizing the parameters of Support vector machine is proposed.Finally,the algorithm based on Tabu algorithm and RBF neural network for predicting the network security situation is defined.To verify the priority of the proposed model,the data generated from the virtual network are regarded as the simulation data,and this model is compared with the other methods.The simulation shows this method can predict effectively with the high prediction accuracy during a nearly similar simulation time.

关 键 词：网络安全态势 禁忌遗传算法 支持向量机 训练误差 预测 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]