A Hybrid Deep Learning-Based State Forecasting Method for Smart Power Grids

Smart power grids are one of the most complex cyber-physical systems, delivering electricity from power generation stations to consumers. It is critically important to know exactly the current state of the system as well as its state variation tendency; consequently, state estimation and state forecasting are widely used in smart power grids. Given that state forecasting predicts the system state ahead of time, it can enhance state estimation because state estimation is highly sensitive to measurement corruption due to the bad data or communication failures. In this paper, a hybrid deep learningbased method is proposed for power system state forecasting. The proposed method leverages Convolutional Neural Network (CNN) for predicting voltage magnitudes and a Deep Recurrent Neural Network (RNN) for predicting phase angels. The proposed CNN-RNN model is evaluated on the IEEE 118-bus benchmark. The results demonstrate that the proposed CNNRNN model achieves better results than the existing techniques in the literature by reducing the normalized Root Mean Squared Error (RMSE) of predicted voltages by 10%. The results also show a 65% and 35% decrease in the average and maximum absolute error of voltage magnitude forecasting. Keywords—forecasting, smart power grid, deep learning, recurrent neural network, convolutional neural network

[1]  Razvan Pascanu,et al.  How to Construct Deep Recurrent Neural Networks , 2013, ICLR.

[2]  Hadis Karimipour,et al.  Parallel relaxation-based joint dynamic state estimation of large-scale power systems , 2016 .

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

[4]  G. Sheblé,et al.  Power generation operation and control — 2nd edition , 1996 .

[5]  M.D. Ilic,et al.  Electric power system static state estimation through Kalman filtering and load forecasting , 2008, 2008 IEEE Power and Energy Society General Meeting - Conversion and Delivery of Electrical Energy in the 21st Century.

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

[7]  M.Th. Schilling,et al.  Revealing gross errors in critical measurements and sets via forecasting-aided state estimators , 2001 .

[8]  Venkata Dinavahi,et al.  Extended Kalman Filter-Based Parallel Dynamic State Estimation , 2016, IEEE Transactions on Smart Grid.

[9]  Venkata Dinavahi,et al.  Parallel Domain-Decomposition-Based Distributed State Estimation for Large-Scale Power Systems , 2016, IEEE Transactions on Industry Applications.

[10]  Hadis Karimipour,et al.  Power System Dynamic State Estimation Using Smooth Variable Structure Filter , 2019, 2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[11]  Z. Morvaj.  A mathematical model of an electric power system for dynamic state estimation , 1985 .

[12]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[13]  Lamine Mili,et al.  A Short-Term Nodal Voltage Phasor Forecasting Method Using Temporal and Spatial Correlation , 2016, IEEE Transactions on Power Systems.

[14]  M. Hassanzadeh,et al.  Power system state forecasting using regression analysis , 2012, 2012 IEEE Power and Energy Society General Meeting.

[15]  Hadis Karimipour,et al.  Robust Massively Parallel Dynamic State Estimation of Power Systems Against Cyber-Attack , 2018, IEEE Access.

[16]  Gang Wang,et al.  Real-Time Power System State Estimation and Forecasting via Deep Unrolled Neural Networks , 2018, IEEE Transactions on Signal Processing.

[17]  Jun Hasegawa,et al.  Dynamic state estimation including anomaly detection and identification for power systems , 1982 .

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

[19]  Venkata Dinavahi,et al.  Accelerated parallel WLS state estimation for large-scale power systems on GPU , 2013, 2013 North American Power Symposium (NAPS).

[20]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.