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

Title: Data-Driven Probabilistic Anomaly Detection for Electricity Market under Cyber Attacks

Conference · · 2021 American Control Conference (ACC)
; ;

Information and communication technologies have been widely used in smart grid for efficient operation. However, these technologies are vulnerable to malicious cyber attacks, which may lead to severe reliability and economic issues. Recently, a variety of data-driven anomaly detection approaches have been explored to detect potential cyber attacks in smart grids. In this paper, we researched on the electricity market data aiming to identify anomalies from the locational marginal prices (LMPs) and provide a new indicator for potential cyber attacks in power grids. Specifically, a novel data-driven probabilistic anomaly detection framework is proposed for electricity market, which consists of three major components: long short-term memory (LSTM) based deterministic electricity price forecasting, probabilistic electricity price forecasting and anomaly detection. This framework is tested on a model-based electricity market simulator under two types of cyber attacks, i.e., load redistribution attack (LRA) and price responsive attack (PRA). Numerical results on the simulated LMPs show that the proposed framework is capable of detecting data anomalies over these attacks.

Research Organization:
Raytheon Technologies Research Center
Sponsoring Organization:
USDOE Office of Cybersecurity, Energy Security, and Emergency Response (CESER)
DOE Contract Number:
OE0000899
OSTI ID:
2217218
Journal Information:
2021 American Control Conference (ACC), Conference: 2021 American Control Conference (ACC), New Orleans, LA, USA
Country of Publication:
United States
Language:
English

References (15)

A two-step short-term probabilistic wind forecasting methodology based on predictive distribution optimization journal March 2019
Multi-distribution ensemble probabilistic wind power forecasting journal April 2020
Modeling Load Redistribution Attacks in Power Systems journal June 2011
False Data Injection on State Estimation in Power Systems—Attacks, Impacts, and Defense: A Survey journal April 2017
Integrity Attacks on Real-Time Pricing in Electric Power Grids
  • Tan, Rui; Krishna, Varun Badrinath; Yau, David K. Y.
  • ACM Transactions on Information and System Security, Vol. 18, Issue 2 https://doi.org/10.1145/2790298
journal July 2015
Protecting the Grid Against MAD Attacks journal July 2020
Dynamic Load Altering Attacks Against Power System Stability: Attack Models and Protection Schemes journal July 2018
Power Consumption Predicting and Anomaly Detection Based on Long Short-Term Memory Neural Network conference April 2019
Grid Shock: Coordinated Load-Changing Attacks on Power Grids: The Non-Smart Power Grid is Vulnerable to Cyber Attacks as Well
  • Dabrowski, Adrian; Ullrich, Johanna; Weippl, Edgar R.
  • ACSAC 2017: 2017 Annual Computer Security Applications Conference, Proceedings of the 33rd Annual Computer Security Applications Conference https://doi.org/10.1145/3134600.3134639
conference December 2017
Detecting Data Integrity Attacks on Correlated Solar Farms Using Multi-layer Data Driven Algorithm conference May 2018
Distributed Internet-Based Load Altering Attacks Against Smart Power Grids journal December 2011
False data injection attacks against state estimation in electric power grids journal May 2011
Optimal Deep Learning LSTM Model for Electric Load Forecasting using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches † journal June 2018
Conditional aggregated probabilistic wind power forecasting based on spatio-temporal correlation journal December 2019
Using quantile regression to extend an existing wind power forecasting system with probabilistic forecasts journal January 2006

Similar Records

Related Subjects

29 ENERGY PLANNING, POLICY, AND ECONOMY
cyber security
anomaly detection
machine learning
probabilistic forecasting
locational marginal price (LMP).