Modeling and forecasting electric daily peak loads using abductive networks

Abstract Forecasting the daily peak load is important for secure and profitable operation of modern power utilities. Machine learning techniques including neural networks have been used for this purpose. This paper proposes the alternative modeling approach of abductive networks, which offers simpler and more automated model synthesis. Resulting analytical input–output models automatically select influential inputs, give better insight and explanations, and allow comparison with other empirical models. Developed using peak load and extreme temperature data for 5 years and evaluated on the sixth year, a model forecasts next-day peak loads with an overall mean absolute percentage error (MAPE) of 2.50%, outperforming neural network models and flat forecasting for the same data. Two methods are described for forecasting daily peak loads up to 1 week ahead through iterative use of the next-day model or using seven dedicated models. Effects of varying model complexity are considered, and simplified analytical expressions are derived for the peak load. Proposals are made for further improving the forecasting accuracy.

[1]  Stanley J. Farlow,et al.  Self-Organizing Methods in Modeling: Gmdh Type Algorithms , 1984 .

[2]  S. J. Kiartzis,et al.  Short-term load forecasting using neural networks , 1995 .

[3]  Y.-Y. Hsu,et al.  Design of artificial neural networks for short - term load forecasting , 1991 .

[4]  F. Frost,et al.  Determining the influence of input parameters on BP neural network output error using sensitivity analysis , 1999, Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300).

[5]  J.R. McDonald,et al.  A specification of neural network applications in the load forecasting problem , 1992, [Proceedings 1992] The First IEEE Conference on Control Applications.

[6]  M. M. Elkateb,et al.  Hybrid adaptive techniques for electric-load forecast using ANN and ARIMA , 2000 .

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

[8]  Y. Fukuyama,et al.  Peak load forecasting using analyzable structured neural network , 2001, 2001 IEEE Power Engineering Society Winter Meeting. Conference Proceedings (Cat. No.01CH37194).

[9]  T. Onoda.  Next day's peak load forecasting using an artificial neural network , 1993, [1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems.

[10]  Alireza Khotanzad,et al.  ANNSTLF-Artificial Neural Network Short-Term Load Forecaster- generation three , 1998 .

[11]  S. Muto,et al.  Regression based peak load forecasting using a transformation technique , 1994 .

[12]  M.A. Aboul-Magd,et al.  An artificial neural network model for electrical daily peak load forecasting with an adjustment for holidays , 2001, LESCOPE 01. 2001 Large Engineering Systems Conference on Power Engineering. Conference Proceedings. Theme: Powering Beyond 2001 (Cat. No.01ex490).

[13]  Keith C. Drake,et al.  Abductive networks , 1990, Defense, Security, and Sensing.

[14]  R.E. Abdel-Aal.  Short-term hourly load forecasting using abductive networks , 2004, IEEE Transactions on Power Systems.

[15]  A.J.R. Reis,et al.  NeuroDem-a neural network based short term demand forecaster , 2001, 2001 IEEE Porto Power Tech Proceedings (Cat. No.01EX502).

[16]  Magdi S. Mahmoud,et al.  Cascaded artificial neural networks for short-term load forecasting , 1997 .

[17]  S. J. Farlow.  SEARCHING FOR STRUCTURE: THE GMDH ALGORITHM , 1984 .

[18]  Kevin Tomsovic.  Neural networks applications in power systems , 1997 .

[19]  Manoel Fernando Tenorio,et al.  Self-organizing network for optimum supervised learning , 1990, IEEE Trans. Neural Networks.

[20]  R. E. Abdel-Aal,et al.  A machine-learning approach to modelling and forecasting the minimum temperature at Dhahran, Saudi Arabia , 1994 .

[21]  F.H.F. Leung,et al.  Tuning of the structure and parameters of neural network using an improved genetic algorithm , 2001, IECON'01. 27th Annual Conference of the IEEE Industrial Electronics Society (Cat. No.37243).

[22]  Moon-Hee Park,et al.  Short-term Load Forecasting Using Artificial Neural Network , 1992 .

[23]  Akihiko Yokoyama,et al.  Next day peak load forecasting using a multilayer neural network with an additional learning , 1993, [1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems.

[24]  G. Gross,et al.  Short-term load forecasting , 1987, Proceedings of the IEEE.

[25]  Ahmed Z. Al-Garni,et al.  Modelling and forecasting monthly electric energy consumption in eastern Saudi Arabia using abductive networks , 1997 .

[26]  M. K. Soni,et al.  Artificial Neural Network-Based Peak Load Forecasting Using Conjugate Gradient Methods , 2002, IEEE Power Engineering Review.

[27]  T. Funabashi,et al.  One-Hour-Ahead Load Forecasting Using Neural Networks , 2002 .

[28]  Tharam S. Dillon,et al.  Short term load forecasting using an adaptive neural network , 1991 .

[29]  W. Charytoniuk,et al.  Neural network design for short-term load forecasting , 2000, DRPT2000. International Conference on Electric Utility Deregulation and Restructuring and Power Technologies. Proceedings (Cat. No.00EX382).

[30]  R. E. Abdel-Aal,et al.  Modeling and Forecasting the Daily Maximum Temperature Using Abductive Machine Learning , 1995 .

[31]  H. W. Lewis.  Intelligent hybrid load forecasting system for an electric power company , 2001, SMCia/01. Proceedings of the 2001 IEEE Mountain Workshop on Soft Computing in Industrial Applications (Cat. No.01EX504).