An LSTM-based Anomaly Classification Framework for Power Electronics Dominated Grids

The power electronics dominated grid (PEDG) is a paradigm shift which will see an increase of distributed energy resources (DERs) for power generation. As the PEDG becomes prevalent, grid anomalies must be detected and mitigated. Detection of these systems must be adaptive to changing grid topologies, and thus present an opportunity for data-driven solutions run by local and supervisory controllers in the PEDG. This work presents a line-to-line fault detection scheme built upon the long short-term memory (LSTM) neural network to determine quickly when line-to-line faults occur. The training process and data collection of the proposed line-to-line LSTM based fault detection can be extended to a multi-class classifier for detection of other anomalies in PEDG. The performance of the proposed LSTM based anomaly detection is validated via several case studies. The results demonstrate promising performance for real-time and effective anomaly detection in less than 20 ms to prevent catastrophic event in PEDG.

[1]  Amin Y. Fard,et al.  Real-Time AI-Based Anomaly Detection and Classification in Power Electronics Dominated Grids , 2023, IEEE Journal of Emerging and Selected Topics in Industrial Electronics.

[2]  Mengchu Zhou,et al.  A Transfer Learning-Based Method to Detect Insulator Faults of High-Voltage Transmission Lines via Aerial Images: Distinguishing Intact and Broken Insulator Images , 2022, IEEE Systems, Man, and Cybernetics Magazine.

[3]  Jianbo Yi,et al.  An Analytical Fault Diagnosis Method: Component Relation and Event Relationship Description Matrices , 2022, IEEE Industry Applications Magazine.

[4]  M. Shadmand,et al.  Artificial Intelligence based Anomaly Detection and Classification for Grid-Interactive Cascaded Multilevel Inverters , 2022, 2022 3rd International Conference on Smart Grid and Renewable Energy (SGRE).

[5]  M. Shadmand,et al.  Smart Battery Cells for Maximum Utilization in Power Electronics Dominated Grids , 2022, 2022 3rd International Conference on Smart Grid and Renewable Energy (SGRE).

[6]  M. Shadmand,et al.  Resilient Model based Predictive Control Scheme Inspired by Artificial Intelligence Methods for Grid-Interactive Inverters , 2021, 2021 6th IEEE Workshop on the Electronic Grid (eGRID).

[7]  M. Shadmand,et al.  A Self-learning Scheme to Detect and Mitigate the Impact of Model Parameters Imperfection in Predictive Controlled Grid-tied Inverter , 2021, 2021 IEEE 22nd Workshop on Control and Modelling of Power Electronics (COMPEL).

[8]  M. Shadmand,et al.  Enforcing Coherency in the Cluster of Grid-forming Inverters in Power Electronics-Dominated Grid , 2021, 2021 IEEE 22nd Workshop on Control and Modelling of Power Electronics (COMPEL).

[9]  Andrey Yablokov,et al.  Remote Fault Localization Based on Synchronized Two-Sided Measurement: Study of the Algorithm and the Prototype Digital Device , 2021, IEEE Industry Applications Magazine.

[10]  Daniel Nikovski,et al.  Distribution Fault Location Using Graph Neural Network with Both Node and Link Attributes , 2021, 2021 IEEE PES Innovative Smart Grid Technologies Europe (ISGT Europe).

[11]  Ahmad Arshan Khan,et al.  On the Stability of the Power Electronics-Dominated Grid: A New Energy Paradigm , 2020, IEEE Industrial Electronics Magazine.

[12]  Gehao Sheng,et al.  A Fault Diagnosis Method of Power Transformer Based on Cost Sensitive One-Dimensional Convolution Neural Network , 2020, 2020 5th Asia Conference on Power and Electrical Engineering (ACPEE).

[13]  Ping Ma,et al.  Detection and Identification of Cyber and Physical Attacks on Distribution Power Grids With PVs: An Online High-Dimensional Data-Driven Approach , 2019, IEEE Journal of Emerging and Selected Topics in Power Electronics.

[14]  Bin Duan,et al.  Deep Convolution Neural Network Based Fault Detection and Identification for Modular Multilevel Converters , 2018, 2018 IEEE Power & Energy Society General Meeting (PESGM).

[15]  Ahmad Abdullah,et al.  Ultrafast Transmission Line Fault Detection Using a DWT-Based ANN , 2018, IEEE Transactions on Industry Applications.

[16]  Farzad R. Salmasi,et al.  Detection of false data injection attacks against state estimation in smart grids based on a mixture Gaussian distribution learning method , 2017, IET Cyper-Phys. Syst.: Theory & Appl..

[17]  Vivienne Sze,et al.  Efficient Processing of Deep Neural Networks: A Tutorial and Survey , 2017, Proceedings of the IEEE.

[18]  Changyun Wen,et al.  Adaptive cyber-physical system attack detection and reconstruction with application to power systems , 2016 .

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

[20]  Fei Hu,et al.  Detection of Faults and Attacks Including False Data Injection Attack in Smart Grid Using Kalman Filter , 2014, IEEE Transactions on Control of Network Systems.

[21]  B. Lu,et al.  A Literature Review of IGBT Fault Diagnostic and Protection Methods for Power Inverters , 2009, 2008 IEEE Industry Applications Society Annual Meeting.

[22]  A.M.S. Mendes,et al.  Voltage source inverter fault diagnosis in variable speed AC drives, by the average current Park's vector approach , 1999, IEEE International Electric Machines and Drives Conference. IEMDC'99. Proceedings (Cat. No.99EX272).

[23]  S. Hochreiter,et al.  Long Short-Term Memory , 1997, Neural Computation.

[24]  R. Peuget,et al.  Fault detection and isolation on a PWM inverter by knowledge-based model , 1997, IAS '97. Conference Record of the 1997 IEEE Industry Applications Conference Thirty-Second IAS Annual Meeting.

[25]  Haibo He,et al.  Q-Learning-Based Vulnerability Analysis of Smart Grid Against Sequential Topology Attacks , 2017, IEEE Transactions on Information Forensics and Security.

[26]  F.W. Fuchs,et al.  Performance of diagnosis methods for IGBT open circuit faults in three phase voltage source inverters for AC variable speed drives , 2005, 2005 European Conference on Power Electronics and Applications.