Modeling and Detection of Future Cyber-Enabled DSM Data Attacks
Abstract
Demand-Side Management (DSM) is an essential tool to ensure power system reliability and stability. In future smart grids, certain portions of a customer’s load usage could be under the automatic control of a cyber-enabled DSM program, which selectively schedules loads as a function of electricity prices to improve power balance and grid stability. In this scenario, the security of DSM cyberinfrastructure will be critical as advanced metering infrastructure and communication systems are susceptible to cyber-attacks. Such attacks, in the form of false data injections, can manipulate customer load profiles and cause metering chaos and energy losses in the grid. The feedback mechanism between load management on the consumer side and dynamic price schemes employed by independent system operators can further exacerbate attacks. To study how this feedback mechanism may worsen attacks in future cyber-enabled DSM programs, we propose a novel mathematical framework for (i) modeling the nonlinear relationship between load management and real-time pricing, (ii) simulating residential load data and prices, (iii) creating cyber-attacks, and (iv) detecting said attacks. In this framework, we first develop time-series forecasts to model load demand and use them as inputs to an elasticity model for the price-demand relationship in the DSM loop. This workmore »
- Authors:
-
- Lehigh Univ., Bethlehem, PA (United States). Dept. of Electrical and Computer Engineering
- Lehigh Univ., Bethlehem, PA (United States). Faculty of Electrical and Computer Engineering
- Lehigh Univ., Bethlehem, PA (United States). Faculty of Industrial and Systems Engineering
- Publication Date:
- Research Org.:
- Univ. of Arkansas, Fayetteville, AR (United States)
- Sponsoring Org.:
- USDOE Office of Electricity (OE)
- OSTI Identifier:
- 1801317
- Grant/Contract Number:
- OE0000779
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Energies
- Additional Journal Information:
- Journal Volume: 13; Journal Issue: 17; Journal ID: ISSN 1996-1073
- Publisher:
- MDPI
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; Energy & Fuels; demand side management; demand response; cyber-physical systems; dynamic pricing; load forecasting; attack detection
Citation Formats
Hatalis, Kostas, Zhao, Chengbo, Venkitasubramaniam, Parv, Snyder, Larry, Kishore, Shalinee, and Blum, Rick S. Modeling and Detection of Future Cyber-Enabled DSM Data Attacks. United States: N. p., 2020.
Web. doi:10.3390/en13174331.
Hatalis, Kostas, Zhao, Chengbo, Venkitasubramaniam, Parv, Snyder, Larry, Kishore, Shalinee, & Blum, Rick S. Modeling and Detection of Future Cyber-Enabled DSM Data Attacks. United States. https://doi.org/10.3390/en13174331
Hatalis, Kostas, Zhao, Chengbo, Venkitasubramaniam, Parv, Snyder, Larry, Kishore, Shalinee, and Blum, Rick S. Fri .
"Modeling and Detection of Future Cyber-Enabled DSM Data Attacks". United States. https://doi.org/10.3390/en13174331. https://www.osti.gov/servlets/purl/1801317.
@article{osti_1801317,
title = {Modeling and Detection of Future Cyber-Enabled DSM Data Attacks},
author = {Hatalis, Kostas and Zhao, Chengbo and Venkitasubramaniam, Parv and Snyder, Larry and Kishore, Shalinee and Blum, Rick S.},
abstractNote = {Demand-Side Management (DSM) is an essential tool to ensure power system reliability and stability. In future smart grids, certain portions of a customer’s load usage could be under the automatic control of a cyber-enabled DSM program, which selectively schedules loads as a function of electricity prices to improve power balance and grid stability. In this scenario, the security of DSM cyberinfrastructure will be critical as advanced metering infrastructure and communication systems are susceptible to cyber-attacks. Such attacks, in the form of false data injections, can manipulate customer load profiles and cause metering chaos and energy losses in the grid. The feedback mechanism between load management on the consumer side and dynamic price schemes employed by independent system operators can further exacerbate attacks. To study how this feedback mechanism may worsen attacks in future cyber-enabled DSM programs, we propose a novel mathematical framework for (i) modeling the nonlinear relationship between load management and real-time pricing, (ii) simulating residential load data and prices, (iii) creating cyber-attacks, and (iv) detecting said attacks. In this framework, we first develop time-series forecasts to model load demand and use them as inputs to an elasticity model for the price-demand relationship in the DSM loop. This work then investigates the behavior of such a feedback loop under intentional cyber-attacks. We simulate and examine load-price data under different DSM-participation levels with three types of random additive attacks: ramp, sudden, and point attacks. We conduct two investigations for the detection of DSM attacks. The first studies a supervised learning approach, with various classification models, and the second studies the performance of parametric and nonparametric change point detectors. Results conclude that higher amounts of DSM participation can exacerbate ramp and sudden attacks leading to better detection of such attacks, especially with supervised learning classifiers. We also find that nonparametric detection outperforms parametric for smaller user pools, and random point attacks are the hardest to detect with any method.},
doi = {10.3390/en13174331},
journal = {Energies},
number = 17,
volume = 13,
place = {United States},
year = {Fri Aug 21 00:00:00 EDT 2020},
month = {Fri Aug 21 00:00:00 EDT 2020}
}
Works referenced in this record:
Load forecasting, dynamic pricing and DSM in smart grid: A review
journal, February 2016
- Khan, Ahsan Raza; Mahmood, Anzar; Safdar, Awais
- Renewable and Sustainable Energy Reviews, Vol. 54
A Nonparametric Change-Point Control Chart
journal, April 2010
- Hawkins, Douglas M.; Deng, Qiqi
- Journal of Quality Technology, Vol. 42, Issue 2
Demand side management in smart grid: A review and proposals for future direction
journal, February 2014
- Gelazanskas, Linas; Gamage, Kelum A. A.
- Sustainable Cities and Society, Vol. 11
Demand Side Management: Demand Response, Intelligent Energy Systems, and Smart Loads
journal, August 2011
- Palensky, Peter; Dietrich, Dietmar
- IEEE Transactions on Industrial Informatics, Vol. 7, Issue 3
Short-Term Load Forecasting Using General Exponential Smoothing
journal, March 1971
- Christiaanse, W.
- IEEE Transactions on Power Apparatus and Systems, Vol. PAS-90, Issue 2
An ensemble approach for short-term load forecasting by extreme learning machine
journal, May 2016
- Li, Song; Goel, Lalit; Wang, Peng
- Applied Energy, Vol. 170
Automatic Block-Length Selection for the Dependent Bootstrap
journal, December 2004
- Politis, Dimitris N.; White, Halbert
- Econometric Reviews, Vol. 23, Issue 1
On a Test of Whether one of Two Random Variables is Stochastically Larger than the Other
journal, March 1947
- Mann, H. B.; Whitney, D. R.
- The Annals of Mathematical Statistics, Vol. 18, Issue 1
Triple seasonal methods for short-term electricity demand forecasting
journal, July 2010
- Taylor, James W.
- European Journal of Operational Research, Vol. 204, Issue 1
A Review of False Data Injection Attacks Against Modern Power Systems
journal, July 2017
- Liang, Gaoqi; Zhao, Junhua; Luo, Fengji
- IEEE Transactions on Smart Grid, Vol. 8, Issue 4
Smart pricing scheme: A multi-layered scoring rule application
journal, June 2014
- Chakraborty, Shantanu; Ito, Takayuki; Senjyu, Tomonobu
- Expert Systems with Applications, Vol. 41, Issue 8
The GLRT for statistical process control of autocorrelated processes
journal, December 1999
- Apley, Daniel W.; Shi, Jianjun
- IIE Transactions, Vol. 31, Issue 12
Matplotlib: A 2D Graphics Environment
journal, January 2007
- Hunter, John D.
- Computing in Science & Engineering, Vol. 9, Issue 3
Pattern-based local linear regression models for short-term load forecasting
journal, January 2016
- Dudek, Grzegorz
- Electric Power Systems Research, Vol. 130
Electricity demand load forecasting of the Hellenic power system using an ARMA model
journal, March 2010
- Pappas, S. Sp.; Ekonomou, L.; Karampelas, P.
- Electric Power Systems Research, Vol. 80, Issue 3
Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network
journal, January 2019
- Kong, Weicong; Dong, Zhao Yang; Jia, Youwei
- IEEE Transactions on Smart Grid, Vol. 10, Issue 1
Detecting Stealthy False Data Injection Using Machine Learning in Smart Grid
journal, September 2017
- Esmalifalak, Mohammad; Liu, Lanchao; Nguyen, Nam
- IEEE Systems Journal, Vol. 11, Issue 3
Integrity Data Attacks in Power Market Operations
journal, December 2011
- Xie, Le; Mo, Yilin; Sinopoli, Bruno
- IEEE Transactions on Smart Grid, Vol. 2, Issue 4
Machine Learning Methods for Attack Detection in the Smart Grid
journal, August 2016
- Ozay, Mete; Esnaola, Inaki; Yarman Vural, Fatos Tunay
- IEEE Transactions on Neural Networks and Learning Systems, Vol. 27, Issue 8
Demand Side Management using a multi-criteria ϵ-constraint based exact approach
journal, June 2018
- Batista, André Costa; Batista, Lucas S.
- Expert Systems with Applications, Vol. 99
A Review of Short Term Load Forecasting using Artificial Neural Network Models
journal, January 2015
- Baliyan, Arjun; Gaurav, Kumar; Mishra, Sudhansu Kumar
- Procedia Computer Science, Vol. 48
Autonomous Demand-Side Management Based on Game-Theoretic Energy Consumption Scheduling for the Future Smart Grid
journal, December 2010
- Mohsenian-Rad, Amir-Hamed; Wong, Vincent W. S.; Jatskevich, Juri
- IEEE Transactions on Smart Grid, Vol. 1, Issue 3
A new hybrid Modified Firefly Algorithm and Support Vector Regression model for accurate Short Term Load Forecasting
journal, October 2014
- Kavousi-Fard, Abdollah; Samet, Haidar; Marzbani, Fatemeh
- Expert Systems with Applications, Vol. 41, Issue 13
A Review of Short Term Load Forecasting using Artificial Neural Network Models
journal, January 2015
- Baliyan, Arjun; Gaurav, Kumar; Mishra, Sudhansu Kumar
- Procedia Computer Science, Vol. 48
The GLRT for statistical process control of autocorrelated processes
journal, December 1999
- Apley, Daniel W.; Shi, Jianjun
- IIE Transactions, Vol. 31, Issue 12
GridLAB-D: An open-source power systems modeling and simulation environment
conference, April 2008
- Chassin, D. P.; Schneider, K.; Gerkensmeyer, C.
- 2008 IEEE/PES Transmission and Distribution Conference and Exposition
Demand Side Management in Smart Grid Using Heuristic Optimization
journal, September 2012
- Logenthiran, Thillainathan; Srinivasan, Dipti; Shun, Tan Zong
- IEEE Transactions on Smart Grid, Vol. 3, Issue 3