Detection of false data injection attacks against power systems using a CNN-LSSVM model
The new cyber-physical power system is crucial for achieving dual carbon goals. However， novel false data injection attacks targeting state estimation can bypass existing security detection mechanisms， significantly challenging the secure operation of power systems. To detect false data in state est...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
zhejiang electric power
2024-11-01
|
| Series: | Zhejiang dianli |
| Subjects: | |
| Online Access: | https://zjdl.cbpt.cnki.net/WKE3/WebPublication/paperDigest.aspx?paperID=6f46cd80-bea4-4038-ad65-a3fcdde13814 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The new cyber-physical power system is crucial for achieving dual carbon goals. However， novel false data injection attacks targeting state estimation can bypass existing security detection mechanisms， significantly challenging the secure operation of power systems. To detect false data in state estimation， the deceptive characteristics of malicious attacks are analyzed using the AC power grid model as the research object. By combining the data spatial feature extraction capabilities of convolutional neural networks （CNN） with the data classification abilities of least squares support vector machine （LSSVM）， this paper develops an attack detection model using CNN-LSSVM. The model’s effectiveness is verified using data from IEEE 14-bus power system， achieving a detection accuracy of 94.6%. |
|---|---|
| ISSN: | 1007-1881 |