摘要
传统异常节点识别方法存在效率较低、精准度较差的局限性,为解决以上问题,现提出基于离散Kalman滤波的计算机网络通信异常节点识别方法。首先,基于离散Kalman滤波构建通信节点测量信道模型,使系统的平方误差降至最小,从而为离散过程的优化设计提供递推算法,其次,提取计算机网络通信异常节点特征,将所有的异常进攻事件都分割成不同的数据集合,最后,实现计算机网络通信异常节点的定位并识别。实验结果证明:基于离散Kalman滤波的计算机网络通信异常节点识别方法识别准确率可达到99%以上,能够准确识别出异常节点,具有较高的识别精度。
The traditional identification method of abnormal nodes has the limitations of low ef-ficiency and poor accuracy.In order to solve the above problems,the identification method of computer network communication based on discreteKalman filter is proposed.Firstly,the com-munication node measurement channel model is constructed based on discrete Kalman filtering,which minimizes the square error of the system and thus provides recursive algorithm for the optimization design of discrete process.Secondly,extracting the abnormal node features of com-putcr nctwork communication,dividing all the abnormal attack cvents into different data scts.Finally,realizing the positioning and identification of computer network communication abnor-mal nodes.The experimental results show that the identification accuracy of computer network communication abnormal nodes based on discrete Kalman filtering can reach more than 99%,which can accurately identify abnormal nodes and have high identification accuracy.
作者
黄丽芳
HUANG Lifang(School of information management Minnan University of science and Technology,Fujian,Shishi,362700,China)
出处
《长江信息通信》
2024年第6期58-60,共3页
Changjiang Information & Communications
基金
闽南理工学院,智能工业互联网与数字化管理科技创新团队,项目类型:科技创新团队项目,项目编号:23XTD114。
关键词
计算机网络
通信节点
离散Kalman滤波
异常识别
computer network
communication node
discreteKalman filtering
anomaly identi-fication
