Unlock instant, AI-driven research and patent intelligence for your innovation.

A false data injection attack detection method based on pca and bp neural network

A BP neural network, fake data technology, applied in the field of fake data injection attack detection, can solve problems such as life impact, failure to operate normally, damage to the normal operation of the power grid, etc.

Active Publication Date: 2021-09-14
GUANGDONG UNIV OF TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Recently, a new type of attack (called False Data Injection (FDI)) was introduced, which cannot be detected by traditional Bad Data Detection (BDD) using state estimation, and Hiding arbitrary deviations in the value of the estimated state seriously damages the normal operation of the power grid. Normal operation; in 2015, the power system in some areas of Ukraine suffered a cyber attack, causing a large-scale power outage, which had a great impact on people's lives

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A false data injection attack detection method based on pca and bp neural network
  • A false data injection attack detection method based on pca and bp neural network
  • A false data injection attack detection method based on pca and bp neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] This embodiment provides a false data injection attack detection method based on PCA and BP neural network, such as figure 1 , including the following steps:

[0064] S1: Obtain the measured values ​​of each sensor in the smart grid through the control center of the smart grid z is an m×n matrix, Both are 1×n matrices;

[0065] S2: In order to overcome the problems of overfitting and data sparseness caused by too high dimensionality, PCA dimensionality reduction technology is used for dimensionality reduction, and the measured values ​​of each sensor Perform PCA dimension reduction to obtain the feature data set after dimension reduction z' is an m×r matrix, r≤n, Both are 1×r matrices;

[0066] S3: Inject false data into a part of the data in the feature data group after dimensionality reduction, and attach a label of false_label to -1 to each group of data in a part of the data injected with false data, and add a label of -1 to the feature data group after di...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a false data injection attack detection method based on PCA and BP neural network. The invention adopts a principal component analysis method (Principal Component Analysis, PCA) to perform dimensionality reduction processing on measurement data. Then, the dimensionally reduced data is used as the training sample of the BP neural network, and training is carried out by adding false data to some of the samples and marking them as attack samples, and the model obtained through training can effectively detect whether there is a false data injection attack . The invention improves the accuracy rate and reduces the training time by using the PCA technology to reduce the dimension of the extracted data, and simultaneously uses the BP neural network to effectively detect the attack value of the false data injection attack.

Description

technical field [0001] The present invention relates to the technical field of power system security, and more specifically, to a method for detecting false data injection attacks based on PCA and BP neural networks. Background technique [0002] An aging electricity sector, coupled with increased demand from industrial and residential customers, is a major motivation for policymakers to develop a roadmap for the next generation of electricity systems, known as smart grids. In a smart grid, overall monitoring costs will decrease, but at the same time, the risk of cyber-attacks may increase. Recently, a new type of attack (called False Data Injection (FDI)) was introduced, which cannot be detected by traditional Bad Data Detection (BDD) using state estimation, and Hiding arbitrary deviations in the value of the estimated state seriously damages the normal operation of the power grid. Normal operation; In 2015, the power system in some areas of Ukraine suffered a cyber attac...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): H04L29/06
CPCH04L63/1416H04L63/1466Y02D30/50
Inventor 刘俊辉刘义杨超谢胜利
Owner GUANGDONG UNIV OF TECH