计算机工程 ›› 2019, Vol. 45 ›› Issue (4): 119-123,129.doi: 10.19678/j.issn.1000-3428.0049685

• 安全技术 • 上一篇    下一篇

基于word2vec的配电网恶意控制指令检测算法

郑佩祥1,陈彬1,卢昕2,徐文渊2   

  1. 1.国网福建省电力有限公司,福州 350003; 2.浙江大学 电气工程学院,杭州 310027
  • 收稿日期:2017-12-13 出版日期:2019-04-15 发布日期:2019-04-15
  • 作者简介:郑佩祥(1970—),男,高级工程师,主研方向为智能配电网安全;陈彬,高级工程师;卢昕,硕士研究生;徐文渊,教授、博士。
  • 基金项目:

    国家高技术研究发展计划(2015AA050202);国家电网公司科技项目(52130415000P)。

Malicious Control Command Detection Algorithm in Power Distribution Network Based on word2vec

ZHENG Peixiang1,CHEN Bin1,LU Xin2,XU Wenyuan2   

  1. 1.State Grid Fujian Electric Power Company,Fuzhou 350003,China; 2.College of Electrical Engineering,Zhejiang University,Hangzhou 310027,China
  • Received:2017-12-13 Online:2019-04-15 Published:2019-04-15

摘要:

现有的配电网恶意控制指令检测方法基于电力系统运行规则,但规则维护困难、规则匹配耗时较长。根据配电网上行测量信息和下行控制指令之间存在的上下文一致性关系,提出基于word2vec的恶意控制指令检测算法。在配电网仿真平台模拟各类工况并获取标注数据集,结果表明,该算法能够取得100%的精确度和87.2%的召回率,具有较高的检测精度。

关键词: 配电网, 恶意控制指令, 上下文, word2vec模型, 异常检测

Abstract:

The existing detection method of malicious control command of distribution network is based on the operating rules of power system,but the rules are difficult to maintain and the rule matching takes a long time.According to the context consistency relationship between the uplink measurement information of the distribution network and the downlink control instructions,a malicious control detection algorithm based on word2vec is proposed.Simulating various working conditions on the power distribution network simulation platform and obtaining the labeled data set,the results show that the algorithm can achieve 100% accuracy and 87.2% recall rate,and has high detection accuracy.

Key words: power distribution network, malicious control command, context, word2vec model, abnormal detection

中图分类号: