Neural Network-Based Model Design for Short-Term Load Forecast in Distribution Systems

Accurate forecasts of electrical substations are mandatory for the efficiency of the Advanced Distribution Automation functions in distribution systems. The paper describes the design of a class of machine-learning models, namely neural networks, for the load forecasts of medium-voltage/low-voltage substations. We focus on the methodology of neural network model design in order to obtain a model that has the best achievable predictive ability given the available data. Variable selection and model selection are applied to electrical load forecasts to ensure an optimal generalization capacity of the neural network model. Real measurements collected in French distribution systems are used to validate our study. The results show that the neural network-based models outperform the time series models and that the design methodology guarantees the best generalization ability of the neural network model for the load forecasting purpose based on the same data.

[1]  M. Sydulu,et al.  Non iterative-state estimation based neural network for short term load forecasting of distribution systems , 2009, 2009 IEEE Power & Energy Society General Meeting.

[2]  Gérard Dreyfus,et al.  Withdrawing an example from the training set: An analytic estimation of its effect on a non-linear parameterised model , 2000, Neurocomputing.

[3]  P. J. Santos,et al.  Designing the input vector to ANN-based models for short-term load forecast in electricity distribution systems , 2007 .

[4]  Hojjat Adeli,et al.  Fuzzy clustering approach for accurate embedding dimension identification in chaotic time series , 2003, Integr. Comput. Aided Eng..

[5]  Isabelle Guyon,et al.  Assessment Methods , 2018, A Practical Guide to Toxicology and Human Health Risk Assessment.

[6]  Gérard Dreyfus,et al.  Local Overfitting Control via Leverages , 2002, Neural Computation.

[7]  P. P. Bedekar,et al.  Comparative analysis of hourly load forecast for a small load area , 2012, 2012 International Conference on Computing, Electronics and Electrical Technologies (ICCEET).

[8]  Qiang Ji,et al.  Comparison of different BP neural network models for short-term load forecasting , 2010, 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems.

[9]  Ming-Wei Chang,et al.  Load forecasting using support vector Machines: a study on EUNITE competition 2001 , 2004, IEEE Transactions on Power Systems.

[10]  W. Marsden.  I and J , 2012 .

[11]  Kenneth Levenberg.  A METHOD FOR THE SOLUTION OF CERTAIN NON – LINEAR PROBLEMS IN LEAST SQUARES , 1944 .

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

[13]  Sheng Chen,et al.  Orthogonal least squares methods and their application to non-linear system identification , 1989 .

[14]  Gérard Dreyfus,et al.  Ranking a Random Feature for Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[15]  Ching-Lai Hor,et al.  Analyzing the impact of weather variables on monthly electricity demand , 2005, IEEE Transactions on Power Systems.

[16]  P. McSharry,et al.  A comparison of univariate methods for forecasting electricity demand up to a day ahead , 2006 .

[17]  J. D. McDonald,et al.  A real-time implementation of short-term load forecasting for distribution power systems , 1994 .

[18]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[19]  Andrea Garulli,et al.  Load forecasting for active distribution networks , 2011, 2011 2nd IEEE PES International Conference and Exhibition on Innovative Smart Grid Technologies.

[20]  V.H. Ferreira,et al.  Complexity Control of Neural Models for Load Forecasting , 2005, Proceedings of the 13th International Conference on, Intelligent Systems Application to Power Systems.

[21]  S. A. Villalba,et al.  Hybrid demand model for load estimation and short term load forecasting in distribution electric systems , 2000 .

[22]  Saifur Rahman,et al.  Input variable selection for ANN-based short-term load forecasting , 1998 .

[23]  A. J. Pires,et al.  Load forecasting, the importance of the probability “tails” in the definition of the input vector , 2013, 4th International Conference on Power Engineering, Energy and Electrical Drives.

[24]  W. Charytoniuk,et al.  Nonparametric regression based short-term load forecasting , 1998 .

[25]  V.H. Hinojosa,et al.  Short-Term Load Forecasting Using Fuzzy Inductive Reasoning and Evolutionary Algorithms , 2010, IEEE Transactions on Power Systems.

[26]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[27]  A. Germond,et al.  Heterogeneous artificial neural network for short term electrical load forecasting , 1995 .

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

[29]  Joao M.C. Sousa,et al.  Short-term load forecasting using information obtained from low voltage load profiles , 2009, 2009 International Conference on Power Engineering, Energy and Electrical Drives.

[30]  Gérard Dreyfus,et al.  Neural networks - methodology and applications , 2005 .

[31]  George G. Karady,et al.  Advancement in the application of neural networks for short-term load forecasting , 1992 .

[32]  Yuan-Kang Wu.  Short-term forecasting for distribution feeder loads with consumer classification and weather dependent regression , 2007, 2007 IEEE Lausanne Power Tech.

[33]  M. Faiazy,et al.  Short Term Load Prediction of a Distribution Network based on an Artificial Intelligent Method , 2013 .

[34]  P. P. Bedekar,et al.  Input Vector Comparison for Hourly Load Forecast of Small Load Area Using Artificial Neural Network , 2012, 2012 International Conference on Communication Systems and Network Technologies.

[35]  A.P. Alves da Silva,et al.  Toward Estimating Autonomous Neural Network-Based Electric Load Forecasters , 2007, IEEE Transactions on Power Systems.

[36]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[37]  A.J. Conejo,et al.  Day-ahead electricity price forecasting using the wavelet transform and ARIMA models , 2005, IEEE Transactions on Power Systems.

[38]  B. De Moor,et al.  Short-term load forecasting, profile identification, and customer segmentation: a methodology based on periodic time series , 2005, IEEE Transactions on Power Systems.

[39]  S. Koopman,et al.  An Hourly Periodic State Space Model for Modelling French National Electricity Load , 2007 .

[40]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[41]  James W. Taylor,et al.  Triple seasonal methods for short-term electricity demand forecasting , 2010, Eur. J. Oper. Res..

[42]  J. Nowicka-Zagrajek,et al.  Modeling electricity loads in California: ARMA models with hyperbolic noise , 2002, Signal Process..

[43]  Frederic Wurtz,et al.  Time series method for short-term load forecasting using smart metering in distribution systems , 2011, 2011 IEEE Trondheim PowerTech.

[44]  Fred Collopy,et al.  How effective are neural networks at forecasting and prediction? A review and evaluation , 1998 .

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

[46]  P. Siano,et al.  Combined Operations of Renewable Energy Systems and Responsive Demand in a Smart Grid , 2011, IEEE Transactions on Sustainable Energy.