Power load forecasting using extended normalised radial basis function networks

Neural networks are currently finding practical applications, ranging from 'soft' regulatory control in consumer products, to the accurate modelling of nonlinear systems. Load forecasting is an important component for power system energy management system. Precise load forecasting helps the electric utility to make unit commitment decisions, reduce spinning reserve capacity and schedule device maintenance plan properly. In this paper we analyse the problem of short term load forecasting and propose a novel neural network scheme based on the Extended Normalised Radial Basis Function network. The Bayesian Ying Yang Expectation Maximisation algorithm has been used with novel splitting operations to determine a network size and parameter set. The results, utilising data from Eastern Slovakian Energy Board, are then compared with that of an MLP neural network.

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

[2]  Vassilis S. Kodogiannis.  Comparison of advanced learning algorithms for short-term load forecasting , 2000, J. Intell. Fuzzy Syst..

[3]  Vassilis Kodogiannis,et al.  Intelligent systems for computer-assisted clinical endoscopic image analysis , 2004 .

[4]  R. Engle,et al.  Modelling peak electricity demand , 1992 .

[5]  E. M. Anagnostakis,et al.  A study of advanced learning algorithms for short-term load forecasting , 1999 .

[6]  Ajith Abraham,et al.  Short Term Load Forecasting Models in Czech Republic Using Soft Computing Paradigms , 2004, ArXiv.

[7]  Chuin-Shan Chen,et al.  Customer short term load forecasting by using ARIMA transfer function model , 1995, Proceedings 1995 International Conference on Energy Management and Power Delivery EMPD '95.

[8]  John N. Lygouras,et al.  Artificial Odor Discrimination System Using Electronic Nose and Neural Networks for the Identification of Urinary Tract Infection , 2008, IEEE Transactions on Information Technology in Biomedicine.

[9]  S. Vemuri,et al.  Neural network based short term load forecasting , 1993 .

[10]  Shangyou Hao,et al.  An implementation of a neural network based load forecasting model for the EMS , 1994 .

[11]  Tie-Mao Peng.  AN IMPLEMENTATION OF A NEURAL NETWORK BASED LOAD FORECASTING MODEL €OR THE EMS Alex D. papalexopoulos Sfrangyou Hao , 1994 .

[12]  Georges Kariniotakis,et al.  Load Forecasting Using Dynamic High-Orderr Neural Networks , 1993, Proceedings. Joint International Power Conference Athens Power Tech,.

[13]  Naonori Ueda,et al.  EM algorithm with split and merge operations for mixture models , 2000 .

[14]  Vassilis S. Kodogiannis,et al.  The use of gas-sensor arrays to diagnose urinary tract infections , 2005, Int. J. Neural Syst..

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

[16]  Lei Xu,et al.  RBF nets, mixture experts, and Bayesian Ying-Yang learning , 1998, Neurocomputing.

[17]  Ivica Kostanic,et al.  Principles of Neurocomputing for Science and Engineering , 2000 .

[18]  Marios M. Polycarpou,et al.  High-order neural network structures for identification of dynamical systems , 1995, IEEE Trans. Neural Networks.

[19]  A. Papalexopoulos,et al.  Forecasting power market clearing price and quantity using a neural network method , 2000, 2000 Power Engineering Society Summer Meeting (Cat. No.00CH37134).