Abstract
Two methods for constructing a neural network map of stochastic systems from input-output time series are presented. Extension of the iterated map to multiple-step predictions outside the training data set is through use of a novel hierarchical architecture, based on forward time-shifting of the general NARMAX model which is subsumed by the Werbos’ time-lagged recurrent network in each level of the hierarchy. The proposed methodology only requires a partial knowledge of the system model orders. A number of numerical examples is given, one of which is on multiple-step-ahead forecasting of an hourly municipal water consumption time series. The test cases demonstrate that the proposed hierarchical mapping idea is valid.
This is a preview of subscription content, log in via an institution to check access.
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
Athans, M., and D. Willner,“A practical scheme for adaptive aircraft flight control systems,” Symp. on Parameter Estimation Techniques and Applications in Aircraft Flight Testing, NASA Fit. Res. Ctr., Edwards AFB, April 1973.
Billings, S.A., H.B. Jamaluddin, and S. Chen, “Properties of neural networks with applications to modelling non-linear dynamical systems,” Int. J. Control, 45, 1, 193–224, 1992.
Chen, S. and S. A. Billing, “Representations of non-linear systems: the NARMAX model,” Int. J. Control, Vol. 49, No. 3, 1013–1032, 1989.
Goodwin, G.C., and K.S. Sin, Adaptive Filtering Prediction and Control, Prentice-Hall, Englewood Cliffs, New Jersey, 1984.
Kashyap, R.L., and A.R. Rao, Dynamic Stochastic Models from Empirical Data, Academic Press, N.Y. 1976.
Landau, I.D.,“Elimination of the real positivity condition in the design of parallel MRAS,” IEEE Trans. Auto. Control 23, 1015–1020, 1978.
Ljung, L. System Identification Theory for the User. Prentice-Hall, Englewood-Cliff, N.J. 1987.
Lowe, D. and A.R. webb, “Time series prediction by adaptive networks: a dynamical systems perspective,” IEE Proceedings-F Vol. 138, No.1, 17–24,1991.
Narendra, K.S., and K. Parthasarathy,“Identification and control of dynamical systems using neural networks,” IEEE Transactions on Neural Networks, Vol. 1, No. 1, pp. 4–26, 1990.
Priestley, M.B., Non-linear and Non-stationary Time Series Analysis, Academic Press, N.Y., 1988.
Rumelhart D. E., and J. L. McClelland, Parallel distributed processing: explorations in microstructure of cognition, MIT Press, 1986.
Sastri, T. “Neural networks for detection of process change in manufacturing systems,” Proceedings of the Joint US/German Conference on New Directions for Operations Research in Manufacturing, National Institute of Standards and Technology, Gaithersburg, MD, July 30–31, 1991.
Sastri, T. and C.O. Malave, “Direct learning and knowledge updating in neural nets”, Proceedings of the Artificial Neural Networks in Engineering, November 15–18, 1992, St. Louis, MO.)
Stengel, R. F., Stochastic Optimal Control Theory and Application, Wiley, N.Y. 1986.
Werbos, P.J., “Neurocontrol and related techniques,” in Maren, A.J., C.T. Harston, and R.M. Pap (Eds.), Handbook of Neural Computing Application. Academic Press, New York [1990].
Werbos, P.J., T. McAvoy, and T. Su. “Neural networks, system identification and control in the chemical process industries,” in White, D., and D. Sofge (Eds.), Handbook of Intelligent Control. Van Nostrand, New York 1992.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin· Heidelberg
About this paper
Cite this paper
Sastri, T. (1993). Multiple-Step-Ahead Prediction by Hierarchical Neural Networks. In: Fandel, G., Gulledge, T., Jones, A. (eds) Operations Research in Production Planning and Control. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-78063-9_33
Download citation
DOI: https://doi.org/10.1007/978-3-642-78063-9_33
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-78065-3
Online ISBN: 978-3-642-78063-9
eBook Packages: Springer Book Archive