基于改进支持向量机的电力物联网入侵检测方法

Intrusion Detection Method for Power Internet of Things Based on Modified Support Vector Machine

针对传统入侵检测方法存在精度不高、耗时长等问题,提出基于改进支持向量机的电力物联网入侵检测方法。对电力物联网数据进行标准化处理,采用粒子群优化方法改进支持向量机关键参数,构建支持向量机检测模型;输入标准化处理完成的数据,通过支持向量机模型训练完成入侵检测研究。实验结果表明,所提方法的检测精度高达93.5%,检测耗时最高仅为8 s,相比传统方法具有明显优势,为电力物联网安全稳定运行提供了基础保障。

In response to the problems of low accuracy and long time consumption of traditional intrusion detection methods,a power IoT intrusion detection method based on modified support vector machine is proposed.By standardizing power IoT data and improving key parameters of SVM via particle swarm optimization,the detection model of support vector machine is established.The study on intrusion detection is performed by using the standardized power IoT data to train the support vector machine model.The experimental results show that the proposed method has a high detection accuracy of 93.5%with maximum detection time cost of only 8 s,is far superior to traditional methods,and helps guarantee safe and stable operation of power Internet of Things.