skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Deep Learning-Based Data Forgery Detection in Automatic Generation Control

Abstract

Automatic Generation Control (AGC) is a key control system in the power grid. It is used to calculate the Area Control Error (ACE) based on frequency and tie-line power flow between balancing areas, and then adjust power generation to maintain the power system frequency in an acceptable range. However, attackers might inject malicious frequency or tie-line power flow measurements to mislead AGC to do false generation correction which will harm the power grid operation. Such attacks are hard to be detected since they do not violate physical power system models. In this work, we propose algorithms based on Neural Network and Fourier Transform to detect data forgery attacks in AGC. Different from the few previous work that rely on accurate load prediction to detect data forgery, our solution only uses the ACE data already available in existing AGC systems. In particular, our solution learns the normal patterns of ACE time series and detects abnormal patterns caused by artificial attacks. Evaluations on the real ACE dataset show that our methods have high detection accuracy.

Authors:
 [1];  [1]
  1. Univ. of Arkansas, Fayetteville, AR (United States)
Publication Date:
Research Org.:
University of Arkansas
Sponsoring Org.:
USDOE Office of Electricity (OE)
OSTI Identifier:
1406254
DOE Contract Number:  
OE0000779
Resource Type:
Conference
Resource Relation:
Conference: IEEE Conference on Communications and Network Security (CNS): IEEE International Workshop on Cyber-Physical Systems Security (CPS-Sec), Las Vegas, NV (United States), 9-11 Oct 2017
Country of Publication:
United States
Language:
English
Subject:
32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION; Power grid; AGC; data forgery attack; deep learning; attack detection

Citation Formats

Zhang, Fengli, and Li, Qinghua. Deep Learning-Based Data Forgery Detection in Automatic Generation Control. United States: N. p., 2017. Web. doi:10.1109/CNS.2017.8228705.
Zhang, Fengli, & Li, Qinghua. Deep Learning-Based Data Forgery Detection in Automatic Generation Control. United States. https://doi.org/10.1109/CNS.2017.8228705
Zhang, Fengli, and Li, Qinghua. 2017. "Deep Learning-Based Data Forgery Detection in Automatic Generation Control". United States. https://doi.org/10.1109/CNS.2017.8228705. https://www.osti.gov/servlets/purl/1406254.
@article{osti_1406254,
title = {Deep Learning-Based Data Forgery Detection in Automatic Generation Control},
author = {Zhang, Fengli and Li, Qinghua},
abstractNote = {Automatic Generation Control (AGC) is a key control system in the power grid. It is used to calculate the Area Control Error (ACE) based on frequency and tie-line power flow between balancing areas, and then adjust power generation to maintain the power system frequency in an acceptable range. However, attackers might inject malicious frequency or tie-line power flow measurements to mislead AGC to do false generation correction which will harm the power grid operation. Such attacks are hard to be detected since they do not violate physical power system models. In this work, we propose algorithms based on Neural Network and Fourier Transform to detect data forgery attacks in AGC. Different from the few previous work that rely on accurate load prediction to detect data forgery, our solution only uses the ACE data already available in existing AGC systems. In particular, our solution learns the normal patterns of ACE time series and detects abnormal patterns caused by artificial attacks. Evaluations on the real ACE dataset show that our methods have high detection accuracy.},
doi = {10.1109/CNS.2017.8228705},
url = {https://www.osti.gov/biblio/1406254}, journal = {},
number = ,
volume = ,
place = {United States},
year = {Mon Oct 09 00:00:00 EDT 2017},
month = {Mon Oct 09 00:00:00 EDT 2017}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share: