摘要
当前检测方法一般为目标执行检测,检测覆盖范围容易受限,导致误报率增加,为此提出基于加权支持向量机(Support Vector Machine,SVM)的电力通信网络异常流量入侵检测方法研究。先提取异常流量隐性特征,采用动态化的方式打破检测覆盖范围受到的限制。设计动态异常流量检测机制,并以此为基础构建基于加权SVM的通信网络异常流量入侵检测模型,采用交叉跟踪识别的方式来完成入侵检测。测试结果表明,应用所提方法检测时,其误报率控制在15%以下,证明设计方法具有较强的稳定性与针对性,实际应用效果更佳。
At present,the detection method is usually for the target,and the detection coverage is easily limited,which leads to the increase of false alarm rate.Therefore,the research on the intrusion detection method of abnormal traffic in power communication network based on weighted Support Vector Machine(SVM)is proposed.Firstly,the hidden features of abnormal traffic are extracted,and the limitation of detection coverage is broken by dynamic method.The dynamic abnormal traffic detection mechanism is designed,and based on this,the intrusion detection model of abnormal traffic in communication network is constructed based on weighted SVM,and the intrusion detection is completed by cross-tracking identification.The test results show that the false alarm rate is controlled below 15%by using the proposed method,which proves that the design method has strong stability and pertinence,and the practical application effect is better.
作者
孙祥刚
SUN Xianggang(Jiangsu Electric Power Information Technology Co.,Ltd.,Nanjing 210000,China)
出处
《通信电源技术》
2024年第10期91-93,共3页
Telecom Power Technology
关键词
加权支持向量机(SVM)
电力通信
网络异常流量
入侵检测
weighted Support Vector Machine(SVM)
power communication
network abnormal traffic
intrusion detection
