Multi-Task Logistic Low-Ranked Dirty Model for Fault Detection in Power Distribution System

This paper proposes a Multi-task Logistic Low-Ranked Dirty Model (MT-LLRDM) for fault detection in power distribution networks by using the distribution Phasor Measurement Unit (PMU) data. The MT-LLRDM improves the fault detection accuracy by utilizing the similarities in the fault data streams among multiple locations across a power distribution network. The captured similarities supplement the information to the task of fault detection at a location of interest, creating a multi-task learning framework and thereby improving the learning accuracy. The algorithm is validated with real-time PMU streams from a hardware-in-the-loop testbed that emulates real field communication and monitoring conditions in distribution networks. The results showed that the MT-LLRDM outperforms other state-of-the-art classification methods using actual synchrophasor data achieved from a power hardware-in-the-loop testbed.

[1]  Panganamala Ramana Kumar,et al.  Power system event classification via dimensionality reduction of synchrophasor data , 2014, 2014 IEEE 8th Sensor Array and Multichannel Signal Processing Workshop (SAM).

[2]  Yuxun Zhou,et al.  Shape Preserving Incremental Learning for Power Systems Fault Detection , 2019, IEEE Control Systems Letters.

[3]  Alexandra von Meier,et al.  Chapter 32 – Every Moment Counts: Synchrophasors for Distribution Networks with Variable Resources , 2017 .

[4]  Ali Jalali,et al.  A Dirty Model for Multiple Sparse Regression , 2011, IEEE Transactions on Information Theory.

[5]  Victor O. K. Li,et al.  Intelligent Fault Detection Scheme for Microgrids With Wavelet-Based Deep Neural Networks , 2019, IEEE Transactions on Smart Grid.

[6]  Costas J. Spanos,et al.  Partial Knowledge Data-Driven Event Detection for Power Distribution Networks , 2018, IEEE Transactions on Smart Grid.

[7]  W. H. Kersting,et al.  Radial distribution test feeders , 1991, 2001 IEEE Power Engineering Society Winter Meeting. Conference Proceedings (Cat. No.01CH37194).

[8]  Jieping Ye,et al.  Learning Incoherent Sparse and Low-Rank Patterns from Multiple Tasks , 2010, TKDD.

[9]  Mladen Kezunovic,et al.  Voltage Sag Data Utilization for Distribution Fault Location , 2011, IEEE Transactions on Power Delivery.

[10]  Ben Taskar,et al.  Joint covariate selection and joint subspace selection for multiple classification problems , 2010, Stat. Comput..

[11]  Ahmad Tbaileh,et al.  Graph Trace Analysis: An object-oriented power flow, verifications and comparisons , 2017 .

[12]  Shahram Kazemi.  Reliability evaluation of smart distribution grids , 2011 .

[13]  Marc Teboulle,et al.  A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems , 2009, SIAM J. Imaging Sci..

[14]  Jiayu Zhou,et al.  Integrating low-rank and group-sparse structures for robust multi-task learning , 2011, KDD.

[15]  Hui Wang,et al.  Multitask Bayesian Spatiotemporal Gaussian Processes for Short-Term Load Forecasting , 2020, IEEE Transactions on Industrial Electronics.

[16]  Sami Ekici,et al.  Classification of power system disturbances using support vector machines , 2009, Expert Syst. Appl..

[17]  Yuxun Zhou,et al.  Multivariate Deep Causal Network for Time Series Forecasting in Interdependent Networks , 2018, 2018 IEEE Conference on Decision and Control (CDC).

[18]  Yuxun Zhou,et al.  Causal Markov Elman Network for Load Forecasting in Multinetwork Systems , 2019, IEEE Transactions on Industrial Electronics.

[19]  Amir Safdarian,et al.  A MIP Model for Risk Constrained Switch Placement in Distribution Networks , 2019, IEEE Transactions on Smart Grid.

[20]  Mario Paolone,et al.  Fault detection and faulted line identification in active distribution networks using synchrophasors-based real-time state estimation , 2017 .

[21]  Han Zou,et al.  Nonparametric Event Detection in Multiple Time Series for Power Distribution Networks , 2019, IEEE Transactions on Industrial Electronics.

[22]  Matthias Stifter,et al.  Real-Time Simulation and Hardware-in-the-Loop Testbed for Distribution Synchrophasor Applications , 2018 .

[23]  Luigi Vanfretti,et al.  The OpenPMU Platform for Open-Source Phasor Measurements , 2013, IEEE Transactions on Instrumentation and Measurement.

[24]  Antonio García,et al.  A Comparison of Impedance-Based Fault Location Methods for Power Underground Distribution Systems , 2016 .

[25]  Wenpeng Luan,et al.  Smart Meter Data Analytics for Distribution Network Connectivity Verification , 2015, IEEE Transactions on Smart Grid.

[26]  A. White,et al.  Synchrophasor Monitoring for Distribution Systems : Technical Foundations and Applications , 2018 .

[27]  Yurii Nesterov,et al.  Introductory Lectures on Convex Optimization - A Basic Course , 2014, Applied Optimization.

[28]  Guido Cavraro,et al.  Power Distribution Network Topology Detection With Time-Series Signature Verification Method , 2018, IEEE Transactions on Power Systems.

[29]  Tony Jebara,et al.  Multi-task feature and kernel selection for SVMs , 2004, ICML.

[30]  Ed Cortez,et al.  Distribution Synchrophasors: Pairing Big Data with Analytics to Create Actionable Information , 2018, IEEE Power and Energy Magazine.

[31]  Alireza Shahsavari,et al.  Locating the Source of Events in Power Distribution Systems Using Micro-PMU Data , 2018, IEEE Transactions on Power Systems.