An agent-based approach to power system dynamic state estimation through dual unscented Kalman filter and artificial neural network

AbstractThis paper proposes a novel approach to the power system dynamic state estimation by using the concepts of dynamic artificial neural networks and dual unscented Kalman filter. A dynamic artificial neural network is applied for developing a discrete-time state transition model of power system which is used for one-step-ahead prediction of the state vector. The model is also applicable for the generation of pseudo-measurements while it is needed. The dual unscented Kalman filter estimates the state vector of power system and calculates the weights of the dynamic artificial neural network simultaneously. A multi-agent-based model is utilized to structure the computational architecture of the proposed approach. The autonomous agents are designed to carry out the complex computations needed in the power system dynamic state estimation. The agents distribute multiple execution tasks among themselves, and they share information interactively. The agent-based modeling of the proposed method enhances the computing efficiency through decomposition of the computations among several autonomous agents. The effectiveness of the proposed method is examined through comprehensive simulations. The results guarantee the performance of the proposed approach as a practical solution for the power system dynamic state estimation.

[1]  Greg Zweigle,et al.  Wide‐area monitoring and control using the real time digital simulator and a synchrophasor vector processor , 2011 .

[2]  Conrad Sanderson,et al.  Armadillo: a template-based C++ library for linear algebra , 2016, J. Open Source Softw..

[3]  J.C.S. de Souza,et al.  Forecasting-Aided State Estimation—Part I: Panorama , 2009 .

[4]  Junbo Zhao.  Power System Dynamic State Estimation Considering Measurement Correlations , 2017, IEEE Transactions on Energy Conversion.

[5]  Jianwei Wan,et al.  Neural network-aided adaptive unscented Kalman filter for nonlinear state estimation , 2006, IEEE Signal Processing Letters.

[6]  Danilo P. Mandic,et al.  A normalised real time recurrent learning algorithm , 2000, Signal Process..

[7]  Gexiang Zhang,et al.  Power System Real-Time Monitoring by Using PMU-Based Robust State Estimation Method , 2016, IEEE Transactions on Smart Grid.

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

[9]  Farrokh Aminifar,et al.  Power System Dynamic State Estimation With Synchronized Phasor Measurements , 2014, IEEE Transactions on Instrumentation and Measurement.

[10]  Mohammad Shahidehpour,et al.  Communication and Control in Electric Power Systems: Applications of Parallel and Distributed Processing , 2003 .

[11]  S.D.J. McArthur,et al.  Multi-Agent Systems for Power Engineering Applications—Part I: Concepts, Approaches, and Technical Challenges , 2007, IEEE Transactions on Power Systems.

[12]  M.D. Ilic,et al.  A Kalman Filter Approach to Quasi-Static State Estimation in Electric Power Systems , 2006, 2006 38th North American Power Symposium.

[13]  Hideaki Sakai,et al.  A real-time learning algorithm for a multilayered neural network based on the extended Kalman filter , 1992, IEEE Trans. Signal Process..

[14]  Sujeet Kumar,et al.  Java Agent Development Framework , 2014 .

[15]  Jeffrey K. Uhlmann,et al.  New extension of the Kalman filter to nonlinear systems , 1997, Defense, Security, and Sensing.

[16]  J.C.S. de Souza,et al.  Forecasting-Aided State Estimation—Part II: Implementation , 2009, IEEE Transactions on Power Systems.

[17]  Amir F. Atiya,et al.  An Empirical Comparison of Machine Learning Models for Time Series Forecasting , 2010 .

[18]  Newton G. Bretas,et al.  An iterative dynamic state estimation and bad data processing , 1989 .

[19]  Gexiang Zhang,et al.  PMU based Robust Dynamic State Estimation method for power systems , 2015, 2015 IEEE Power & Energy Society General Meeting.

[20]  Gustavo Valverde,et al.  Impact of Transformer Correlations in State Estimation Using the Unscented Transformation , 2014, IEEE Transactions on Power Systems.

[21]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[22]  Liam Murphy,et al.  Parallel and distributed state estimation , 1995 .

[23]  Nicolas Lhuillier,et al.  FOUNDATION FOR INTELLIGENT PHYSICAL AGENTS , 2003 .

[24]  Shaobu Wang,et al.  An Alternative Method for Power System Dynamic State Estimation Based on Unscented Transform , 2012, IEEE Transactions on Power Systems.

[25]  Jeffrey K. Uhlmann,et al.  Unscented filtering and nonlinear estimation , 2004, Proceedings of the IEEE.

[26]  Gustavo Valverde,et al.  Unscented kalman filter for power system dynamic state estimation , 2011 .

[27]  Kai Sun,et al.  Dynamic State Estimation for Multi-Machine Power System by Unscented Kalman Filter With Enhanced Numerical Stability , 2015, IEEE Transactions on Smart Grid.

[28]  Michael Wooldridge,et al.  Introduction to multiagent systems , 2001 .

[29]  Avinash Kumar Sinha,et al.  Dynamic state estimator using ANN based bus load prediction , 1999 .

[30]  Atif S. Debs,et al.  A Dynamic Estimator for Tracking the State of a Power System , 1970 .

[31]  Tianshu Bi,et al.  A novel hybrid state estimator for including synchronized phasor measurements , 2008 .

[32]  Innocent Kamwa,et al.  Online State Estimation of a Synchronous Generator Using Unscented Kalman Filter From Phasor Measurements Units , 2011, IEEE Transactions on Energy Conversion.

[33]  M. Lehtonen,et al.  Distributed agent-based State estimation for electrical distribution networks , 2005, IEEE Transactions on Power Systems.

[34]  Chia-Nan Ko,et al.  Short-term load forecasting using SVR (support vector regression)-based radial basis function neural network with dual extended Kalman filter , 2013 .

[35]  Hugh F. Durrant-Whyte,et al.  A new method for the nonlinear transformation of means and covariances in filters and estimators , 2000, IEEE Trans. Autom. Control..

[36]  M. Pai.  Energy function analysis for power system stability , 1989 .

[37]  S.D.J. McArthur,et al.  Multi-Agent Systems for Power Engineering Applications—Part II: Technologies, Standards, and Tools for Building Multi-agent Systems , 2007, IEEE Transactions on Power Systems.

[38]  Vedran Kirincic,et al.  A two-step hybrid power system state estimator , 2015 .

[39]  Shihab S Asfour,et al.  Short-Term Forecasting of Electric Loads Using Nonlinear Autoregressive Artificial Neural Networks with Exogenous Vector Inputs , 2017 .

[40]  Nikolaos M. Manousakis,et al.  State estimation and bad data processing for systems including PMU and SCADA measurements , 2011 .

[41]  Heidar Ali Talebi,et al.  Neural Network-Based State Estimation of Nonlinear Systems: Application to Fault Detection and Isolation , 2009 .

[42]  Serena Ng,et al.  Tests for Skewness, Kurtosis, and Normality for Time Series Data , 2005 .

[43]  S. Haykin.  Kalman Filtering and Neural Networks , 2001 .

[44]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.