Smart Grid Anomaly Detection using a Deep Learning Digital Twin
Open accessThe DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index.
Abstract
The power grid is considered to be the most critical piece of infrastructure in the United States because each of the other fifteen critical infrastructures, as defined by the Cyberse-curity and Infrastructure Security Agency (CISA), require the energy sector to properly function. Due the critical nature of the power grid, the ability to detect anomalies in the power grid is of critical importance to prevent power outages, avoid damage to sensitive equipment and to maintain a working power grid. Over the past few decades, the modern power grid has evolved into a large Cyber Physical System (CPS) equipped with wide area monitoring systems (WAMS) and distributed control. As smart technology advances, the power grid continues to be upgraded with high fidelity sensors and measurement devices, such as phasor measurement units (PMUs), that can report the state of the system with a high temporal resolution. However, this influx of data can often become overwhelming to the legacy Supervisory Control and Data Acquisition (SCADA) system, as well as, the power system operator. In this paper, we propose using a deep learning (DL) convolutional neural network (CNN) as a module within the Automatic Network Guardian for ELectrical systems (ANGEL) Digital Twin environment to detect physical faults in a power system. The presented approach uses high fidelity measurement data from the IEEE 9-bus and IEEE 39-bus benchmark power systems to not only detect if there is a fault in the power system but also applies the algorithm to classify which bus contains the fault.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.11231 · Cited by 4,636 · cited 1×
“Some of the recent successes of modern deep learning architectures include ResNet [9], which was able to surpass human accuracy in an image recognition task, and deep reinforcement learning techniques, like AlphaGo [10], which have mastered complex games.”
BackgroundThe Digital Twin Paradigm for Future NASA and U.S. Air Force Vehicles
Glaessgen, E., & Stargel, D. (2012) · 53rd AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference 20th AIAA/ASME/AHS Adaptive Structures Conference 14th AIAA · doi:10.2514/6.2012-1818 · Cited by 3,395 · cited 1×
“Digital Twin technology is widely used in many industries, such as automotive [4] and aerospace [5], to provide greater insight to a deployed system.”
BackgroundTraining with Noise is Equivalent to Tikhonov Regularization
Bishop, C. M. (1995) · Neural Computation · doi:10.1162/neco.1995.7.1.108 · Cited by 1,325
Shaping the digital twin for design and production engineering
Schleich, B., Anwer, N., Mathieu, L., & Wartzack, S. (2017) · CIRP Annals · doi:10.1016/j.cirp.2017.04.040 · Cited by 1,305 · cited 1×
“Digital Twin technology is widely used in many industries, such as automotive [4] and aerospace [5], to provide greater insight to a deployed system.”
BackgroundA Digital-Twin-Assisted Fault Diagnosis Using Deep Transfer Learning
Xu, Y., Sun, Y., Liu, X., & Zheng, Y. (2019) · IEEE Access · doi:10.1109/access.2018.2890566 · Cited by 509
Self-citationNeural Smithing: Supervised Learning in Feedforward Artificial Neural Networks
Reed, R., & Marks, R. J. (1999) · The MIT Press eBooks · doi:10.7551/mitpress/4937.001.0001 · Cited by 470
A Digital Twin Approach for Fault Diagnosis in Distributed Photovoltaic Systems
Jain, P., Poon, J., Singh, J. P., Spanos, C., Sanders, S. R., & Panda, S. K. (2020) · IEEE Transactions on Power Electronics · doi:10.1109/tpel.2019.2911594 · Cited by 462
Cyber‐physical attacks and defences in the smart grid: a survey
He, H., & Yan, J. (2016) · IET Cyber-Physical Systems: Theory & Applications · doi:10.1049/iet-cps.2016.0019 · Cited by 454
Self-citationChen, K., Huang, C., & He, J. (2016) · High Voltage · doi:10.1049/hve.2016.0005 · Cited by 377
An overview of state-of-the-art partial discharge analysis techniques for condition monitoring
Wu, M., Cao, H., Cao, J., Nguyen, H.-L., Gomes, J. B., & Krishnaswamy, S. P. (2015) · IEEE Electrical Insulation Magazine · doi:10.1109/mei.2015.7303259 · Cited by 285
Characterizing and quantifying noise in PMU data
Brown, M., Biswal, M., Brahma, S., Ranade, S. J., & Cao, H. (2016) · 2016 IEEE Power and Energy Society General Meeting (PESGM) · doi:10.1109/pesgm.2016.7741972 · Cited by 251
An Online Power System Stability Monitoring System Using Convolutional Neural Networks
Gupta, A., Gurrala, G., & Sastry, P. S. (2019) · IEEE Transactions on Power Systems · doi:10.1109/tpwrs.2018.2872505 · Cited by 207
Korkali, M., Lev-Ari, H., & Abur, A. (2012) · IEEE Transactions on Power Systems · doi:10.1109/tpwrs.2011.2176351 · Cited by 189
Brosinsky, C., Westermann, D., & Krebs, R. (2018) · 2018 IEEE International Energy Conference (ENERGYCON) · doi:10.1109/energycon.2018.8398846 · Cited by 165
Packet-data anomaly detection in PMU-based state estimator using convolutional neural network
Basumallik, S., Ma, R., & Eftekharnejad, S. (2019) · International Journal of Electrical Power & Energy Systems · doi:10.1016/j.ijepes.2018.11.013 · Cited by 153
Detection of false data injection attacks in smart grids using Recurrent Neural Networks
Ayad, A., Farag, H. E. Z., Youssef, A., & El-Saadany, E. F. (2018) · IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT) · doi:10.1109/isgt.2018.8403355 · Cited by 140
Dynamic state estimation including anomaly detection and identification for power systems
Nishiya, K.-I., Hasegawa, J., & Koike, T. (1982) · IEE Proceedings C Generation Transmission and Distribution · doi:10.1049/ip-c.1982.0032 · Cited by 124
ANGEL: An Intelligent Digital Twin Framework for Microgrid Security
Danilczyk, W., Sun, Y., & He, H. (2019) · 2019 North American Power Symposium (NAPS) · doi:10.1109/naps46351.2019.9000371 · Cited by 112
Self-citationYadav, A., & Swetapadma, A. (2015) · International Journal of Electrical Power & Energy Systems · doi:10.1016/j.ijepes.2014.12.079 · Cited by 86
Dobakhshari, A. S., & Ranjbar, A. M. (2014) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2014.2322977 · Cited by 78
Deep learning neural network for power system fault diagnosis
Wang, Y., Liu, M., & Bao, Z. (2016) · Chinese Control Conference (CCC) · doi:10.1109/chicc.2016.7554408 · Cited by 74
Dynamic state estimation‐based fault locating on transmission lines
Liu, Y., Meliopoulos, A. P. S., Tan, Z., Sun, L., & Fan, R. (2017) · IET Generation Transmission & Distribution · doi:10.1049/iet-gtd.2017.0371 · Cited by 69
Power system tracking and dynamic state estimation
Jain, A., & Shivakumar, N. R. (2009) · IEEE PES Power Systems Conference and Exposition · doi:10.1109/psce.2009.4840192 · Cited by 63
Fault detection in transmission networks of power systems
Saha, S., Aldeen, M., & Tan, C. P. (2011) · International Journal of Electrical Power & Energy Systems · doi:10.1016/j.ijepes.2010.12.026 · Cited by 52
Smart grid testbed for Wide-Area Monitoring and Control systems
Leger, A. S., Spruce, J., Banwell, T. C., & Collins, M. (2016) · IEEE PES Transmission and Distribution Conference and Exhibition · doi:10.1109/tdc.2016.7519995 · Cited by 39
Transmission Line Fault Location Using Deep Learning Techniques
Fan, R., Yin, T., Huang, R., Lian, J. J., & Wang, S. (2019) · North American Power Symposium (NAPS) · doi:10.1109/naps46351.2019.9000224 · Cited by 31
Fault detection and location on electrical distribution system
Lampley, G. C. (2003) · IEEE Rural Electric Power Conference (REPC) · doi:10.1109/repcon.2002.1002288 · Cited by 28
Analysis of Wide Area Monitoring System architectures
Gore, R., & Kande, M. (2015) · IEEE International Conference on Industrial Technology (ICIT) · doi:10.1109/icit.2015.7125272 · Cited by 26
Accurate Fault Classifier and Locator for EHV Transmission Lines Based on Artificial Neural Networks
Hessine, M. B., & Saber, S. B. (2014) · Mathematical Problems in Engineering · doi:10.1155/2014/240565 · Cited by 25
Digital Twin - Concept of a Continuously Adaptive Power System Mirror
Brosinsky, C., Song, X., & Westermann, D. (2019) · Cited by 24
Diagnostic Applications for Micro-Synchrophasor Measurements
von Meier, A., & Arghandeh, R. (2014) · eScholarship (California Digital Library) · Cited by 17
Neutron holography makes its debut
Chang, S. (2016) · Physics Today · doi:10.1063/pt.3.3385 · Cited by 11
CNNPred: CNN-based stock market prediction using several data sourcesPreprint
Hoseinzade, E., & Haratizadeh, S. (2018) · RePEc: Research Papers in Economics · doi:10.48550/arxiv.1810.08923 · Cited by 10
Research works printed but not linked: 2
- 0, Assault on California Power Station Raises Alarm on Potential for Terrorism
- case, 2016, Analysis of the cyber attack on the ukrainian power grid, Electricity Information Sharing and Analysis Center (E-ISAC)
Cited by
Jafari, M., Kavousi-Fard, A., Chen, T., & Karimi, M. (2023) · IEEE Access · doi:10.1109/access.2023.3241588 · Cited by 409
“The state of art technologies like AI techniques are widely utilized for parameter designation [80], [81].”
MethodQian, C., Liu, X., Ripley, C., Qian, M., Liang, F., & Yu, W. (2022) · Future Internet · doi:10.3390/fi14020064 · Cited by 211
Sarker, I. H., Janicke, H., Mohsin, A., Gill, A., & Maglaras, L. (2024) · ICT Express · doi:10.1016/j.icte.2024.05.007 · Cited by 188
Xu, H., Omitaomu, F., Sabri, S., Zlatanova, S., Li, X., & Song, Y. (2024) · Urban Informatics · doi:10.1007/s44212-024-00060-w · Cited by 178
Towards electric digital twin grid: Technology and framework review
Sifat, M. M. H., Choudhury, S. M., Das, S. K., Ahamed, M. H., Muyeen, S. M., Hasan, M. M., Ali, M. F., Tasneem, Z., Islam, M. M., Islam, M. R., et al. (2023) · Energy and AI · doi:10.1016/j.egyai.2022.100213 · Cited by 174
“In this approach a wide-area power distribution or transmission system’s defects might be found and fixed using machine learning algorithms, enabling system monitoring to be done continuously and prevention of further system damage [131] (see Fig.”
Background
Metadata
- Authors
- Danilczyk, W., Sun, Y. L., & He, H.
- Affiliations
- University of Rhode Island (US)
- Venue
- 2020 52nd North American Power Symposium (NAPS)
- Publisher
- IEEE
- Published
- 2021-04-11
- Pages
- 1-6
- OpenAlex
- W3174063337
- Cited by
- 89
- References
- 34
- Citations by year
- 2026: 11 · 2025: 17 · 2024: 24 · 2023: 27 · 2022: 7 · 2021: 3
- FWCI
- 23.94
- Type
- conference paper
- Language
- en
- Open access
- Licence
- Locations
- North American Power Symposium (NAPS) (publishedVersion)
- Journal of Media Literacy Education (submittedVersion, cc-by)
- Funders
- Office of Naval Research (N00014-18-1-2396)
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Power System Optimization and Stability
- Physical Sciences › Engineering › Control and Systems Engineering › Power Systems Fault Detection
- Physical Sciences › Engineering › Control and Systems Engineering › Smart Grid Security and Resilience
- Keywords
- smart grid, anomaly detection, power system fault detection, digital twin, convolutional neural networks, phasor measurement units, WAMS, SCADA, cyber-physical systems, power grid cybersecurity
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.