Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Physics-Guided Deep Learning for Time-Series State Estimation Against False Data Injection Attacks

Conference · · 2019 North American Power Symposium (NAPS)
 [1];
  1. University of central Florida

The modern power grid is a cyber-physical system. While the grid is becoming more intelligent with emerging sensing and communication techniques, new vulnerabilities are introduced and cyber security becomes a major concern. One type of cyber-attacks - False Data Injection Attacks (FDIAs) - exploits the limitations in traditional power system state estimation, and modifies system states without being detected. In this paper, we propose a physics-guided deep learning (PGDL) approach to defend against FDIAs. The PGDL takes real-time measurements as inputs to neural networks, outputs the estimated states, and reconstructs measurements considering power system physics. A deep recurrent neural network - Long Short-Term Memory (LSTM) - is employed to learn the temporal correlations among states. This hybrid learning model leads to a time-series state estimation method to defend against FDIAs. The simulation results using IEEE 14-bus test system demonstrate the accuracy and robustness of the proposed time-series state estimation under FDIAs.

Research Organization:
University of central Florida
Sponsoring Organization:
USDOE
DOE Contract Number:
EE0007998
OSTI ID:
1826288
Journal Information:
2019 North American Power Symposium (NAPS), Journal Name: 2019 North American Power Symposium (NAPS)
Country of Publication:
United States
Language:
English

Similar Records

Physics-Guided Deep Learning for Time-Series State Estimation Against False Data Injection Attacks
Conference · Tue Oct 01 00:00:00 EDT 2019 · 2019 North American Power Symposium (NAPS) · OSTI ID:1826257

Moving-horizon false data injection attack design against cyber–physical systems
Journal Article · Thu May 04 00:00:00 EDT 2023 · Control Engineering Practice · OSTI ID:2417650