电子学报 ›› 2020, Vol. 48 ›› Issue (8): 1552-1557.DOI: 10.3969/j.issn.0372-2112.2020.08.013

所属专题: 机器学习—特征选择

• 学术论文 • 上一篇    下一篇

基于多尺度低秩模型的电力无线接入网异常流量检测方法

周伯阳1, 郭志民1, 王延松2, 阮伟3, 吴春明4, 周宁1, 张伟1, 程国振5   

  1. 1. 国网河南省电力公司电力科学研究院, 河南郑州 450000;
    2. 中兴通讯股份有限公司, 江苏南京 210012;
    3. 浙江大学控制科学与工程学院, 浙江杭州 310027;
    4. 浙江大学计算机科学与技术学院, 浙江杭州 310027;
    5. 国家数字程控交换工程技术研究中心, 河南郑州 450002
  • 收稿日期:2018-04-19 修回日期:2018-06-05 出版日期:2020-08-25 发布日期:2018-06-20
  • 通讯作者: 阮伟
  • 作者简介:周伯阳 男,1986年出生,河南驻马店人,博士,高级工程师.研究方向为电力无线通信安全、智能电网通信技术. E-mail:boyang319@qq.com郭志民 男,1977年出生,河南南阳人,本科,教授级高级工程师,国网河南省电力公司电力科学研究院设备状态评价中心副主任,研究方向为电力系统自动化、电力信息安全. E-mail:zhimin.guo@163.com

An Anomaly Traffic Detection Method Using Multi-resolution Low Rank Model for Wireless Access Network of Electric Power Grids

ZHOU Bo-yang1, GUO Zhi-min1, WANG Yan-song2, RUAN Wei3, WU Chun-ming4, ZHOU Ning1, ZHANG Wei1, CHENG Guo-zhen5   

  1. 1. State Grid Henan Electric Power Research Institute, State Grid Henan Electric Power Company, Zhengzhou, Henan 450000, China;
    2. ZTE Corporation, Nanjing, Jiangsu 210012, China;
    3. College of Control Science and Engineering, Zhejiang University, Hangzhou, Zhejiang 310027, China;
    4. College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang 310027, China;
    5. National Digital Switching System Engineering & Technological R&D Center, Zhengzhou 450002, China
  • Received:2018-04-19 Revised:2018-06-05 Online:2020-08-25 Published:2018-06-20

摘要: 电力无线接入网的安全性对于电网生产至关重要,然而由于其IEC 60870-5-104规约控制数据存在着高维度的特点,且无线信道质量动态变化,难以快速、有效地检测控制数据的异常.鉴于此,本文提出了一种基于多尺度低秩的电力无线网异常流量检测器,首先构建一种规约深度分析的多尺度低秩模型,对其安全特征进行归一化和维度缩减,然后采用改进的递归特征选取和聚焦分类算法实现异常数据的检测.实验结果表明异常流量分类的准确性和维度缩减的性能.

关键词: 电力无线接入网, IEC 60870-5-104, 多尺度低秩模型, 特征选择, 多维尺度分析, 异常流量检测

Abstract: The security of the wireless access network of electric power grids is critical for power grid productions.However,the control data anomalies are difficult to be detected in a fast and effective manner,due to the high dimension of the control protocol data in IEC 60870-5-104 protocol,as well as the dynamics on the quality of wireless channels.To this end,this paper proposes an anomaly traffic detector(ATD)for the wireless network of power girds based on multi-resolution low rank(MRLR)model.Firstly,the ATD is designed with the MRLR for the protocol,to regularize and reduce the security feature dimensions.Secondly,it utilizes the improved recursive feature selection and focused classification algorithms for accurate data anomaly detection.The results demonstrate the accuracy for the classification on data anomalies,and the performance for the dimensionality reduction.

Key words: wireless access networks for power grids, IEC 60870-5-104, multi-resolution low rank model, feature selection, multi-resolution analytics, anomaly traffic detection

中图分类号: