Experience with FNN models for medium term power demand predictions

IEEE Transactions on Power Systems

Volumn 14, Issue 2, 1999, Pages 538-546

  Doveh, E ^a   Feigin, P ^a   Greig, D ^a   Hyams, L ^a  

^a NONE

Author keywords

[No Author keywords available]

Indexed keywords

ELECTRIC LOAD FORECASTING; ELECTRIC POWER UTILIZATION; FEEDFORWARD NEURAL NETWORKS; TIME SERIES ANALYSIS;

POWER DEMAND PREDICTIONS;

ELECTRIC POWER SYSTEMS;

EID: 0032649785     PISSN: 08858950     EISSN: None     Source Type: Journal    
DOI: 10.1109/59.761878     Document Type: Article

References (26)

1. K. HornikM. Stinchcombe, and H. White, "Multilayer feedforward networks are universal approximators," Neural Networks, vol. 2, pp. 359-366, 1989.
2. M. LeshnoV. Y. Lin, A. Pinkus, and S. Schocken, "Multilayer feedforward networks with a non-polynomial activation function can approximate any function," Neural Networks, vol. 6, pp. 861-867, 1993.
3. A. Pinkus"TDI-subspaces of C(R) and some density problems from neural networks," J. Approx. Theory, vol. 85, pp. 269-287, 1996.
4. A. S. Weigend and M. Mangeas"Nonlinear gated experts for time series: Discovering regimes and avoiding overfitting," Internat. J. Neural Systems, vol. 6, pp. 373-399, 1995.
5. K. LiuS. Subaravan, R. R. Shouts, M. T. Manry, C. Kwan, F. L. Lewis, and J. Naccarino, "Comparison of very short-term load forecasting techniques," TEEE Trans. Power Sys., vol. 11, no. 2, pp. 877-882, 1996.
6. A. G. BakirtzisV. Petridis, S. J. Kiartzis, M. C. Alexiadis, and A. H. Maissis, "A neural network short term load forecasting model for the Greek power system," IEEE Trans. Power Sys., vol. 11, no. 2, pp. 858-863, 1996.
7. O. MohammedD. Park, R. Merchant, T. Dinh, C. Tong, A Azeem, J. Farah, and C. Drake, "Practical experiences with an adaptive neural network short-term load forecasting system," IEEE Trans. Power Sys., vol. 10, no. 1, pp. 254-262, 1995.
8. StatlibStatlib S-Archive, 1996, anonymous ftp: lib.stat.cmu.edu from the directory /S OR www site: http://www.stat .cmu.edu/S/
9. T. Chow and L. Chi-Tat"Performance enhancement using nonlinear preprocessing," IEEE Trans. Neur. Net., vol. 7, pp. 1039-1042, 1996.
10. C. M. BishopNeural Networks for Pattern Recognition, Oxford University Press, 1995.
11. B. D. Ripley"Statistical ideas for selecting network architectures," in Neural Networks: Artificial Intelligence and Industrial Applications, B. Kappen and S. Gielen, Eds. 1995, Springer: London.
12. D. H. Wolpert"Stacked generalization," Neural Networks, vol. 5, pp. 241-259, 1992.
13. R. Reed"Pruning algorithms - a survey," IEEE Trans. Neur. Nets., vol. 4, pp. 740-747, 1993.
14. B. D. RipleyPattern Recognition and Neural Networks, Cambridge University Press, 1996.
15. J. Sietsma and R. J. F. Dow"Neural net pruning - why and how," in Proc. IEEE Conf. Neur. Nets, 1988, vol. 1, pp. 325-333.
16. J. Sietsma and R. J. F. Dow"Creating artificial neural networks that generalize," Neural Networks, vol. 4, pp. 67-79, 1991.
17. A. U. LevinT. K. Leen, and J. E. Moody, "Fast pruning using principal components," in Adv. Neur. Inf. Proc. Sys., J. Cowan, G. Tesauro, and J. Alspector, Eds. 1994, vol. 6, Morgan Kaufman.
18. Y. LeCunJ. S. Denker, and S. A. Solla, "Optimal brain damage," in Adv. Neur. Inf. Proc. Sys., David S. Touretsky, Ed. 1990, vol. 2, pp. 598-605, Morgan Kaufman.
19. B. Hassibi and D. G. Stork"Second order derivatives for network pruning: Optimal brain surgeon," in Adv. Neur. Inf. Proc.
20. Sys, S. J. Hanson, J. D. Cowan, and C. L. Giles, Eds. 1993, vol. 5, pp. 164-171, Morgan Kaufman.
21. A. S. WeigendB. A. Huberman, and D. E. Rumelhart, "Predicting the future: A connectionist approach," Internat. J. Neural Systeme, vol. 1, no. 3, pp. 193-209, 1990.
22. J. E. Moody"The effective number of parameters: An analysis of generalization and regularization in nonlinear learning systems," in Adv. Neur. Inf. Proc. Sys., J. Moody, S. Hanson, and R. Lippman, Eds. 1992, vol. 4, pp. 847-854, Morgan Kaufman.
23. H. H. Thodberg"A review of Bayesian neural networks with an application to near infared spectroscopy," IEEE Trans. Neur. Nets, vol. 7, no. 1, pp. 56-72, 1996.
24. D. H. Wolpert"On the use of evidence in neural networks," in Adv. Neur. Inf. Proc. Sys., S. J. Hanson, J. D. Cowan, and C. L. Giles, Eds. 1993, vol. 5, pp. 539-546, Morgan Kaufmann.
25. D. J. C. MacKay"Hyperparameters: Optimize or integrate out?,'1 in Maximum Entropy and Bayesian Methods, G. Heidbreder, Ed. Dordrecht, The Netherlands: Kluwer, 1995.
26. Etti Doveh received her DSc in Statistics at the TechnionIsrael Institute of Technology, in 1992. She is currently working in the Technion Statistics Laboratory on a variety of consulting projects, including development of electric load forecasting models using neural networks and nonparametric regression techniques. Paul Feigin completed a PhD in Statistics at the Australian National University in 1975. He is currently Professor of Statistics in the Faculty of Industrial Engineering and Management at the Technion, Israel Institute of Technology. He is also the head of the Technion Statistics Laboratory. His recent research interests include applied time series analysis, nonparametric regression and experimental design and analysis. Darryl Greig received a PhD in Probability Theory at the University of Melbourne (Australia) in 1995, and was a postdoctoral fellow at the Faculty of Industrial Engineering and Management in the Technion, Israel Institute of Technology. He is currently working for Hewlett Packard Laboratories Israel on document management. His research interests include neural network theory and applications, and stochastic processes with telecommunication applications. Lyne Hyarns received her doctorate in Applied Mathematics and Statistics at Grenoble Scientific University (France) in 1983. She is currently working in .the Statistics Department of the Israeli Electric Company on peak load and energy demand forecasting.