期刊
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
卷 17, 期 3, 页码 1892-1904出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2020.2984315
关键词
Phasor measurement units; Numerical models; Pollution measurement; Power grids; Data models; Mathematical model; Cyber– physical power system; extreme learning machine; false data injection attack (FDIA); quasi-Newton method; state estimation (SE)
类别
资金
- National Natural Science Foundation of China [51907126, U1813212]
- Foundations of Shenzhen and Technology Committee [JCYJ20170817100412488, JCYJ20190808141019, JCYJ20180305124348603]
This article introduces an FDIA model and state reconstruction scheme that can handle both traditional and synchronized measurements, successfully detecting and removing state bias caused by false data injection attacks through the use of extreme learning machine classifier and state forecasting method.
Successful detection of false data injection attacks (FDIAs) and removal of state bias due to FDIAs are essential for ensuring secure power grids operation and control. This article first extends the approximate dc model of FDIA to a more general ac model that can handle both traditional and synchronized measurements. To automatically filter out the established FDIAs, we propose a state reconstruction scheme consisting of a contaminated state separation method, an enhanced bad data identification approach and a state recovery algorithm. In this scheme, a classifier is developed by aggregating a series of extreme learning machines (ELMs) to detect anomaly states caused by FDIAs. Gaussian random distribution and Latin hypercube sampling are adopted to initialize the input weights of base ELMs, which can provide more diversities to enhance the ensemble performance. Then, to identify the exact locations of the compromised measurements, a state forecasting-based bad data identification approach is proposed by exploiting the consistency between the forecasted and the received measurements. Finally, an effective state recovery algorithm applies quasi-Newton method and Armijo line search to address the possible system unobservable problem due to the removal of attacked measurements. Numerical tests on serval IEEE standard test systems verify the efficiency of the proposed FDIA model and state reconstruction scheme.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据