Reservoir Computing Meets Smart Grids: Attack Detection Using Delayed Feedback Networks

A new method for attack detection of smart grids with wind power generators using reservoir computing (RC) is introduced in this paper. RC is an energy-efficient computing paradigm within the field of neuromorphic computing and the delayed feedback networks (DFNs) implementation of RC has shown superior performance in many classification tasks. The combination of temporal encoding, DFN, and a multilayer perceptron (MLP) as the output readout layer is shown to yield performance improvement over existing attack detection methods such as MLPs, support vector machines (SVM), and conventional state vector estimation (SVE) in terms of attack detection in smart grids. The proposed algorithms are shown to be more robust than MLP and SVE in dealing with different variables such as the amplitude of the attack, attack types, and the number of compromised measurements in smart grids. The attack detection rate for the proposed RC-based system is higher than 99%, based on the accuracy metric for the average of 10 000 simulations.

[1]  Seyyed Ali Seyyedsalehi,et al.  Video-based face recognition and image synthesis from rotating head frames using nonlinear manifold learning by neural networks , 2015, Neural Computing and Applications.

[2]  Song Guo,et al.  Big Data Meet Green Challenges: Greening Big Data , 2016, IEEE Systems Journal.

[3]  F. Mechler,et al.  Interspike Intervals, Receptive Fields, and Information Encoding in Primary Visual Cortex , 2000, The Journal of Neuroscience.

[4]  R. FitzHugh.  Impulses and Physiological States in Theoretical Models of Nerve Membrane. , 1961, Biophysical journal.

[5]  Lian Zhao,et al.  Noncommutative Composite Water-Filling for Energy Harvesting and Smart Power Grid Hybrid System With Peak Power Constraints , 2016, IEEE Transactions on Vehicular Technology.

[6]  Eric D Young,et al.  First-spike latency information in single neurons increases when referenced to population onset , 2007, Proceedings of the National Academy of Sciences.

[7]  Xiaojiang Du,et al.  Achieving Efficient Detection Against False Data Injection Attacks in Smart Grid , 2017, IEEE Access.

[8]  Lennert Appeltant.  Reservoir computing based on delay-dynamical systems , 2012 .

[9]  Rongxing Lu,et al.  Defending Against False Data Injection Attacks on Power System State Estimation , 2017, IEEE Transactions on Industrial Informatics.

[10]  Henry Markram,et al.  Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations , 2002, Neural Computation.

[11]  Zahir Tari,et al.  Identification of vulnerable node clusters against false data injection attack in an AMI based Smart Grid , 2015, Inf. Syst..

[12]  Warren B. Powell,et al.  Adaptive Stochastic Control for the Smart Grid , 2011, Proceedings of the IEEE.

[13]  Yang Yi,et al.  Energy Efficient Spiking Temporal Encoder Design for Neuromorphic Computing Systems , 2016, IEEE Transactions on Multi-Scale Computing Systems.

[14]  Khaled Ben Letaief,et al.  Energy harvesting small cell networks: feasibility, deployment, and operation , 2015, IEEE Communications Magazine.

[15]  J. Lisman.  The theta/gamma discrete phase code occuring during the hippocampal phase precession may be a more general brain coding scheme , 2005, Hippocampus.

[16]  Armin Schnettler,et al.  Bad data detection and handling in distribution grid state estimation using artificial neural networks , 2015, 2015 IEEE Eindhoven PowerTech.

[17]  Alecsandru Patrascu,et al.  Cyber Protection of Critical Infrastructures Using Supervised Learning , 2015, 2015 20th International Conference on Control Systems and Computer Science.

[18]  Jian Liu,et al.  Novel Spike based Reservoir Node Design with High Performance Spike Delay Loop , 2016, NANOCOM.

[19]  Mats Forssell,et al.  Hardware Implementation of Artificial Neural Networks , 2015 .

[20]  Benjamin Schrauwen,et al.  An overview of reservoir computing: theory, applications and implementations , 2007, ESANN.

[21]  Lang Tong,et al.  Malicious Data Attacks on the Smart Grid , 2011, IEEE Transactions on Smart Grid.

[22]  O. L. Bekri,et al.  Impact of the wind generator on the power flow in the electric grid , 2014, 3rd International Symposium on Environmental Friendly Energies and Applications (EFEA).

[23]  Yahong Rosa Zheng,et al.  Brain-Inspired Wireless Communications: Where Reservoir Computing Meets MIMO-OFDM , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[24]  Song Guo,et al.  Big Data Meet Green Challenges: Big Data Toward Green Applications , 2016, IEEE Systems Journal.

[25]  Xiao-Jing Wang,et al.  Spike-Frequency Adaptation of a Generalized Leaky Integrate-and-Fire Model Neuron , 2004, Journal of Computational Neuroscience.

[26]  Bo Tang,et al.  Detection of false data attacks in smart grid with supervised learning , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

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

[28]  Ian A. Hiskens,et al.  Control for Renewable Energy and Smart Grids , 2011 .

[29]  Herbert Jaeger,et al.  Reservoir computing approaches to recurrent neural network training , 2009, Comput. Sci. Rev..

[30]  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.

[31]  Atsushi Uchida,et al.  Nonlinear dynamics and chaos synchronization in Mackey-Glass electronic circuits with multiple time-delayed feedback , 2012 .

[32]  Marcelo A. Montemurro,et al.  Spike-Phase Coding Boosts and Stabilizes Information Carried by Spatial and Temporal Spike Patterns , 2009, Neuron.

[33]  Peter Ford Dominey,et al.  On-Line Processing of Grammatical Structure Using Reservoir Computing , 2012, ICANN.

[34]  Huajin Tang,et al.  Precise-Spike-Driven Synaptic Plasticity: Learning Hetero-Association of Spatiotemporal Spike Patterns , 2013, PloS one.

[35]  Yang Yi,et al.  Enabling Sustainable Cyber Physical Security Systems through Neuromorphic Computing , 2018, IEEE Transactions on Sustainable Computing.

[36]  Leslie S Smith,et al.  Neuromorphic systems: past, present and future. , 2010, Advances in experimental medicine and biology.

[37]  L. Appeltant,et al.  Information processing using a single dynamical node as complex system , 2011, Nature communications.

[38]  Haibo He,et al.  Learning from Imbalanced Data , 2009, IEEE Transactions on Knowledge and Data Engineering.

[39]  Yang Yi,et al.  An energy efficient decoding scheme for nonlinear MIMO-OFDM network using reservoir computing , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[40]  H. Vincent Poor,et al.  Machine Learning Methods for Attack Detection in the Smart Grid , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[41]  Yogesh Kumar,et al.  Study of Power and Renewable Systems Modeling and Simulation Tools , 2015 .

[42]  Nicolas Brunel,et al.  Sensory neural codes using multiplexed temporal scales , 2010, Trends in Neurosciences.

[43]  Arindam Basu,et al.  Nullcline-Based Design of a Silicon Neuron , 2010, IEEE Transactions on Circuits and Systems I: Regular Papers.

[44]  S. Soter,et al.  Development of Induction Machines in Wind Power Technology , 2007, 2007 IEEE International Electric Machines & Drives Conference.

[45]  Dipti Srinivasan,et al.  Guest Editorial Special Issue on "Neural Networks and Learning Systems Applications in Smart Grid" , 2016, IEEE Trans. Neural Networks Learn. Syst..

[46]  Song Tan,et al.  Survey of Security Advances in Smart Grid: A Data Driven Approach , 2017, IEEE Communications Surveys & Tutorials.

[47]  R D Zimmerman,et al.  MATPOWER: Steady-State Operations, Planning, and Analysis Tools for Power Systems Research and Education , 2011, IEEE Transactions on Power Systems.

[48]  Herbert Jaeger,et al.  The''echo state''approach to analysing and training recurrent neural networks , 2001 .