Detection of false data injection attacks in smart grids using Recurrent Neural Networks

False Data Injection (FDI) attacks create serious security challenges to the operation of power systems, especially when they are carefully constructed to bypass conventional state estimation bad data detection techniques implemented in the power system control room. This paper investigates the utilization of Recurrent Neural Networks (RNN) as a machine learning technique to detect these FDI attacks. The proposed detection algorithm is validated throughout simulations of FDI in power flow data over the span of five years using IEEE-30 Bus system. The simulation results confirm that the proposed RNN-based algorithm achieves high accuracy in detecting anomalies in the data, by observing the temporal variation in the successive data sequence.

[1]  Hamid Sharif,et al.  A Survey on Cyber Security for Smart Grid Communications , 2012, IEEE Communications Surveys & Tutorials.

[2]  Lang Tong,et al.  On malicious data attacks on power system state estimation , 2010, 45th International Universities Power Engineering Conference UPEC2010.

[3]  Peng Ning,et al.  False data injection attacks against state estimation in electric power grids , 2011, TSEC.

[4]  Allen J. Wood,et al.  Power Generation, Operation, and Control , 1984 .

[5]  A. G. Expósito,et al.  Power system state estimation : theory and implementation , 2004 .

[6]  Aditya Ashok,et al.  Cyber-Physical Attack-Resilient Wide-Area Monitoring, Protection, and Control for the Power Grid , 2017, Proceedings of the IEEE.

[7]  Lindah Kotut,et al.  Survey of Cyber Security Challenges and Solutions in Smart Grids , 2016, 2016 Cybersecurity Symposium (CYBERSEC).

[8]  Arman Sargolzaei,et al.  Detection of Fault Data Injection Attack on UAV Using Adaptive Neural Network , 2016 .

[9]  Rong Zheng,et al.  Detecting Stealthy False Data Injection Using Machine Learning in Smart Grid , 2017, IEEE Systems Journal.

[10]  Husheng Li,et al.  Time Synchronization Attack in Smart Grid: Impact and Analysis , 2013, IEEE Transactions on Smart Grid.

[11]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[12]  Zhao Yang Dong,et al.  A Review of False Data Injection Attacks Against Modern Power Systems , 2017, IEEE Transactions on Smart Grid.

[13]  Wei Yu,et al.  On False Data-Injection Attacks against Power System State Estimation: Modeling and Countermeasures , 2014, IEEE Transactions on Parallel and Distributed Systems.

[14]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[15]  Laurence R. Phillips,et al.  Analysis of operations and cyber security policies for a system of cooperating Flexible Alternating Current Transmission System (FACTS) devices. , 2005 .

[16]  Ronald J. Williams,et al.  Gradient-based learning algorithms for recurrent networks and their computational complexity , 1995 .

[17]  Heejo Lee,et al.  This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination. INVITED PAPER Cyber–Physical Security of a Smart Grid Infrastructure , 2022 .

[18]  Gang Chen,et al.  A Gentle Tutorial of Recurrent Neural Network with Error Backpropagation , 2016, ArXiv.

[19]  Jack Kelly,et al.  Neural NILM: Deep Neural Networks Applied to Energy Disaggregation , 2015, BuildSys@SenSys.

[20]  Mehul Motani,et al.  Detecting False Data Injection Attacks in AC State Estimation , 2015, IEEE Transactions on Smart Grid.

[21]  Sakir Sezer,et al.  Impact of cyber-security issues on Smart Grid , 2011, 2011 2nd IEEE PES International Conference and Exhibition on Innovative Smart Grid Technologies.

[22]  Ying Jun Zhang,et al.  Graphical Methods for Defense Against False-Data Injection Attacks on Power System State Estimation , 2013, IEEE Transactions on Smart Grid.