Abstract
Gradient-based neural network learning algorithms, specifically the backpropagation (BACKPROP), quickpropagation (QUICKPROP), and cascade correlation (CASCOR), have been re-implemented, tested, and compared for making predictions of time series for daily energy (gas) consumption. Daily records of energy consumption form a time series with information that can predict energy demand for a few days. Initially, the basic prediction is made from the past series without taking external influences into consideration. Later, other independent predictive data series can be included to improve prediction. Repeated presentation of hundreds of sample patterns systematically trains a network which converges upon connection configurations that predict expected demand. It has been demonstrated that the learning algorithms can consistently train networks to predict, one-day-ahead over the succeeding year, with the average error reduced to below 20%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Speed in Backpropagation Networks, June 1988, Technical Report, CMU-CS-88-162. Computer Science Department, Carnegie Mellon University, Pittsburgh, PA.
The Cascade-Correlation Learning Architecture, February 1990, Technical Report, CMU-CS-90-100. Computer Science Department, Carnegie Mellon University, Pittsbiirgh, PA.
Rumelhart, D.E., Hinton, G.E., and Williams, R.J. (1986) “Learning Internal Representations by Error Propagation”, In: Parallel Distributed Processing, MIT Press, Vol. 1, pp. 318–362.
Unnikrishnan, K. P. and Venugopal, K. P. “ALOPEX: A correlation-based learning algorithm for feed-forward and recurrent neural networks” R&D Publication GMR-7919, GM Technical Center, MI. (1993)
Unnikrishnan, K. P. and Venugopal, K. P. “Learning in connectionist networks using the ALOPEX algorithm” Proceedings of the International Joint Conference on Neural Networks IJCNN Part I, pp. 926–931. (1992)
Surkan, A.J., Skurikhin, A.N. “Memory neural networks applied to the prediction of daily energy usage,” Proceedings of the World Congress on Neural Networks — San Diego, June 5–9, Volume 2, pages 254–259, (1994) Publisher: Lawrence Erlbaum Associates, Hillsdale, NJ
Sastry, P.S., Santharam, G. and Unnikrishnan, K.P. “Memory neuron networks for identification and control of dynamical systems”, R&D Publication GMR-7916, GM Technical Center, MI (1993)
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1995 Springer-Verlag/Wien
About this paper
Cite this paper
Skurikhin, A.N., Surkan, A.J. (1995). Neural Network Training Compared for BACKPROP QUICKPROP and CASCOR in Energy Control Problems. In: Artificial Neural Nets and Genetic Algorithms. Springer, Vienna. https://doi.org/10.1007/978-3-7091-7535-4_115
Download citation
DOI: https://doi.org/10.1007/978-3-7091-7535-4_115
Publisher Name: Springer, Vienna
Print ISBN: 978-3-211-82692-8
Online ISBN: 978-3-7091-7535-4
eBook Packages: Springer Book Archive