摘要
为有效分析识别有源配电网信息物理系统(cyberphysicalsystem,CPS)状态,提出基于FP-Growth算法的有源配电网信息物理系统网络攻击检测方法。首先分析考虑网络攻击的有源配电网控制模型及CPS网络攻击影响机理,通过实时仿真平台对有源配电网CPS信息侧和物理侧进行监测来获取原始数据;然后通过额定电压、电流值制订数据离散化规则,并根据规则对原始数据进行离散量化处理来生成事件序列。在此基础上,采用FP-Growth算法挖掘历史数据异常信号的频繁项集和强关联关系,通过已有频繁序列特征对新的攻击类别和故障点进行识别,实现对有源配电网CPS网络攻击的检测。最后,仿真实验验证了所提方法的可行性和有效性。
In order to effectively analyze and identify the cyber physical system(CPS)status of active distribution network,a network attack detection method based on FP-Growth algorithm for active distribution network cyber physical system was proposed.Firstly,the active distribution network control model considering network attack and the impact mechanism of CPS network attack were analyzed,and the raw data was obtained by monitoring the CPS information side and physical side of the active distribution network through the real-time simulation platform.Then,the data discretization rules were formulated through the rated voltage and current values,and the original data were discretized and quantized according to the rules to generate event sequences.On this basis,the FP-Growth algorithm was used to mine the frequent items and strong correlations of abnormal signals in historical data,and new attack categories and fault points were identified through the existing frequent sequence features. The detection of CPS network attackon active distribution network was realized. Finally, the feasibility and effectiveness of the proposed methodwere verified by a simulation experiment.
作者
李瑞
刘珊
闫磊
LI Rui;LIU Shan;YAN Lei(State Grid Shanxi Electric Power Research Institute,Taiyuan 030001,China;State Grid Shanxi Electric Power Company,Taiyuan 030021,China)
出处
《电信科学》
北大核心
2024年第11期103-113,共11页
Telecommunications Science
基金
国网山西省电力公司科技项目(No.520530230009)。
