Random vector functional link network for short-term electricity load demand forecasting

Short-term electricity load forecasting plays an important role in the energy market as accurate forecasting is beneficial for power dispatching, unit commitment, fuel allocation and so on. This paper reviews a few single hidden layer network configurations with random weights (RWSLFN). The RWSLFN was extended to eight variants based on the presence or absence of input layer bias, hidden layer bias and direct input-output connections. In order to avoid mapping the weighted inputs into the saturation region of the enhancement nodes' activation function and to suppress the outliers in the input data, a quantile scaling algorithm to re-distribute the randomly weighted inputs is proposed. The eight variations of RWSLFN are assessed using six generic time series datasets and 12 load demand time series datasets. The result shows that the RWSLFNs with direct input-output connections (known as the random vector functional link network or RVFL network) have statistically significantly better performance than the RWSLFN configurations without direct input-output connections, possibly due to the fact that the direct input-output connections in the RVFL network emulate the time delayed finite impulse response (FIR) filter. However the RVFL network has simpler training and higher accuracy than the FIR based two stage neural network. The RVFL network is also compared with some reported forecasting methods. The RVFL network overall outperforms the non-ensemble methods, namely the persistence method, seasonal autoregressive integrated moving average (sARIMA), artificial neural network (ANN). In addition, the testing time of the RVFL network is the shortest while the training time is comparable to the other reported methods. Finally, possible future research directions are pointed out.

[1]  Zhiping Lin,et al.  Predicting time series with wavelet packet neural networks , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[2]  Rahmat-Allah Hooshmand,et al.  A hybrid intelligent algorithm based short-term load forecasting approach , 2013 .

[3]  Robert P. W. Duin,et al.  Feedforward neural networks with random weights , 1992, Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol.II. Conference B: Pattern Recognition Methodology and Systems.

[4]  Wei-Chiang Hong,et al.  Support Vector Regression Model Based on Empirical Mode Decomposition and Auto Regression for Electric Load Forecasting , 2013 .

[5]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[6]  Dong-Chul Park,et al.  A Time Series Data Prediction Scheme Using Bilinear Recurrent Neural Network , 2010, 2010 International Conference on Information Science and Applications.

[7]  Rahmat-Allah Hooshmand,et al.  A new hybrid day-ahead peak load forecasting method for Iran’s National Grid , 2013 .

[8]  J. Ben Hadj Slama,et al.  Day-ahead load forecast using random forest and expert input selection , 2015 .

[9]  Dong-Xiao Niu,et al.  Support Vector Machine Model in Electricity Load Forecasting , 2006, 2006 International Conference on Machine Learning and Cybernetics.

[10]  Dejan J. Sobajic,et al.  Learning and generalization characteristics of the random vector Functional-link net , 1994, Neurocomputing.

[11]  C. L. Philip Chen.  A rapid supervised learning neural network for function interpolation and approximation , 1996, IEEE Trans. Neural Networks.

[12]  Carlos E. Pedreira,et al.  Neural networks for short-term load forecasting: a review and evaluation , 2001 .

[13]  Haidar Samet,et al.  A new hybrid Modified Firefly Algorithm and Support Vector Regression model for accurate Short Term Load Forecasting , 2014, Expert Syst. Appl..

[14]  Grzegorz Dudek,et al.  Short-Term Load Forecasting Using Random Forests , 2014, IEEE Conf. on Intelligent Systems.

[15]  P. N. Suganthan,et al.  A comprehensive evaluation of random vector functional link networks , 2016, Inf. Sci..

[16]  P. McSharry,et al.  Short-Term Load Forecasting Methods: An Evaluation Based on European Data , 2007, IEEE Transactions on Power Systems.

[17]  Paulo Cortez,et al.  Data Mining with , 2005 .

[18]  Dianhui Wang,et al.  Fast decorrelated neural network ensembles with random weights , 2014, Inf. Sci..

[19]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[20]  Yuting Wang,et al.  Very Short-Term Load Forecasting: Wavelet Neural Networks With Data Pre-Filtering , 2013, IEEE Transactions on Power Systems.

[21]  Lipo Wang,et al.  Neural Networks and Wavelet De-Noising for Stock Trading and Prediction , 2013, Time Series Analysis, Modeling and Applications.

[22]  Xin Yao,et al.  Short-Term Load Forecasting with Neural Network Ensembles: A Comparative Study [Application Notes] , 2011, IEEE Computational Intelligence Magazine.

[23]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[24]  Abir Jaafar Hussain,et al.  Time Series Prediction Using Dynamic Ridge Polynomial Neural Networks , 2009, 2009 Second International Conference on Developments in eSystems Engineering.

[25]  J. W. Taylor,et al.  Short-Term Load Forecasting With Exponentially Weighted Methods , 2012, IEEE Transactions on Power Systems.

[26]  Patrick P. K. Chan,et al.  Random forest based ensemble system for short term load forecasting , 2012, 2012 International Conference on Machine Learning and Cybernetics.

[27]  Hesham K. Alfares,et al.  Electric load forecasting: Literature survey and classification of methods , 2002, Int. J. Syst. Sci..

[28]  Alexander J. Smola,et al.  Support Vector Regression Machines , 1996, NIPS.

[29]  Davide Anguita,et al.  Energy Load Forecasting Using Empirical Mode Decomposition and Support Vector Regression , 2013, IEEE Transactions on Smart Grid.

[30]  Mehmet Kurban,et al.  Artificial Intelligence Based Hybrid Structures for Short-Term Load Forecasting Without Temperature Data , 2012, 2012 11th International Conference on Machine Learning and Applications.

[31]  Lipo Wang,et al.  Data Mining With Computational Intelligence , 2006, IEEE Transactions on Neural Networks.

[32]  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 .

[33]  C. L. Philip Chen,et al.  A rapid learning and dynamic stepwise updating algorithm for flat neural networks and the application to time-series prediction , 1999, IEEE Trans. Syst. Man Cybern. Part B.

[34]  Holk Cruse,et al.  Neural networks as cybernetic systems , 1996 .

[35]  Q. Henry Wu,et al.  Electric Load Forecasting Based on Locally Weighted Support Vector Regression , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[36]  P. N. Suganthan,et al.  A Comparative Study of Empirical Mode Decomposition-Based Short-Term Wind Speed Forecasting Methods , 2015, IEEE Transactions on Sustainable Energy.