Hybrid Water Demand Forecasting Model Associating Artificial Neural Network with Fourier Series
Publication: Journal of Water Resources Planning and Management
Volume 138, Issue 3
Abstract
This paper addressed the problem of water-demand forecasting for real-time operation of water supply systems. The present study was conducted to identify the best fit model using hourly consumption data from the water supply system of Araraquara, São Paulo, Brazil. Artificial neural networks (ANNs) were used in view of their enhanced capability to match or even improve on the regression model forecasts. The ANNs used were the multilayer perceptron with the back-propagation algorithm (MLP-BP), the dynamic neural network (DAN2), and two hybrid ANNs. The hybrid models used the error produced by the Fourier series forecasting as input to the MLP-BP and DAN2, called ANN-H and DAN2-H, respectively. The tested inputs for the neural network were selected literature and correlation analysis. The results from the hybrid models were promising, DAN2 performing better than the tested MLP-BP models. DAN2-H, identified as the best model, produced a mean absolute error (MAE) of and for training and test set, respectively, for the prediction of the next hour, which represented about 12% of the average consumption. The best forecasting model for the next 24 hours was again DAN2-H, which outperformed other compared models, and produced a MAE of and for training and test set respectively, which represented about 12% of average consumption.
Get full access to this article
View all available purchase options and get full access to this article.
Acknowledgments
The authors acknowledge the support from the Brazilian Scientific and Technological Development Council (CNPq) and from the Research Support Foundation of São Paulo (FAPESP) for providing the scholarship and grant to the authors, and also from the Araraquara’s Autonomous Department of Water and Sewage (DAAE-Araraquara, SP, Brazil) for providing the time-series data and assistance. The authors would also like to thank the anonymous reviewers for their helpful comments that permitted improvements to the manuscript.
References
Adamowski, J. F. (2008). “Peak daily water demand forecast modeling using artificial neural networks.” J. Water Resour. Plann. Manage.JWRMD5, 134(2), 119–128.
Athanasiadis, I., Mentes, A., Mitkas, P., and Mylopoulos, Y. (2005). “A hybrid agent-based model for estimating residential water demand.” SimulationSIMUA2, 81(3), 175–187.
Bougadis, J., Adamowski, K., and Diduch, R. (2005). Short-term municipal water demand forecasting—Intersciences, Wiley.
Crommelynck, V., Duquesne, C., Mercier, M., and Miniussi, C. (1992). “Daily and hourly water consumption forecasting tools using neural networks.” Proc. of the AWWA’s Annual Computer Specialty Conference, Nashville, TN, 665–676.
Cybenko, G. (1989). “Approximation by superpositions of a sigmoidal function.” Math. Control Signals Syst.MCSYE8, 2(4), 303–314.
Funahashi, K. I. (1989). “On the approximate realization of continuous mappings by neural networks.” Neural Netw.NNETEB, 2(3), 183–192.
Ghiassi, M., and Saidane, H. (2005). “A dynamic architecture for artificial neural networks.” NeurocomputingNRCGEO, 63, 397–413.
Ghiassi, M., Zimbra, D. K., and Saidane, H. (2008). “Urban water demand forecasting with a dynamic artificial neural network model.” J. Water Resour. Plann. Manage.JWRMD5, 134(2), 138–146.
Haykin, S. (1999). Neural network—A comprehensive foundation, 2nd Ed., Prentice Hall, NY.
Hristev, R. H. (2000). “Matrix techniques in artificial neural networks.” Master Science thesis. Univ. of Cantebury, UK.
Humes, A. F. P. C, Melo, I. S. H., Yoshida, L. K., and Martins, W. T. (1984). Noções de cálculo numérico São Paulo, McGraw-Hill.
Jain, A., and Kumar, A. M. (2007). “Hybrid neural network models for hydrologic time series forecasting.” Appl. Soft Comput., 7(2), 585–592.
Jain, A., Ormsbee, L. E. (2002). “Short-term water demand forecast modeling techniques: Conventional methods versus AI.” J. AWWAJAWWA5, 94(7), 64–72.
Jain, A., Varshney, A. K., and Joshi, U. C. (2001). “Short-term water demand forecast modelling at IIT Kanpur using artificial neural networks.” Water Resour. Manage.WRMAEJ, 15(5), 299–321.
JBPCAfill. (2004). “Missing value estimator for Java. V.2.” 〈http://hawaii.aist-nara.ac.jp/~shige-o/tools/BPCAFill.html〉 (Nov. 30, 2009).
Jowitt, P. W., and Xu, C. (1992). “Demand forecasting for water distribution systems.” Civ. Eng. Syst.CESYEE, 9(2), 105–121.
Lim, E. A., and Zainuddin, Z. (2008). “A comparative study of missing value estimation methods: Which method performs better?” International Conference on Electronic Design 2008, IEEE, New York, 1–5.
Maidment, D. R., Miaou, S. P., and Crawford, M. M. (1985). “Transfer function models of daily urban water use.” Water Resour. Res.WRERAQ, 21(4), 425–432.
Miaou, S. P. (1990). “A class of time series Urban water demand models with non-linear climatic effects.” Water Resour. Res.WRERAQ, 26(2), 169–178.
Oba, S., Sato, M., Takemasa, I., Monden, M., Matsubara, K., and Ishii, S. A. (2003). “Bayesian missing value estimation method.” BioinformaticsBOINFP, 19(16), 2088–2096.
Odan, F. K., Ferrero, C. A., Reis, L. F. R., Monard, M. C. (2009). “Análise comparativa dos modelos kNN-TSP e Série de Fourier para previsão de demanda horária para abastecimento de água.” XVIII Simpósio Brasileiro de Recursos Hídricos—ABRH.
Perry, P. F. (1981). “Demand forecasting in water supply networks.” J. Hydraul. Div., 107(HY9), 1077–1087.JYCEAJ
Pulido-Calvo, I., Gutierrez-Estrada, J. C. (2009). “Improved irrigation water demand forecasting using a soft-computing hybrid model.” Biosystems Eng.BEINBJ, 102(2), 202–218.
Shvartser, L., Shamir, U., and Feldeman, M. (1993). “Forecasting hourly water demand by pattern recognition approach.” J. Water Resour. Plann. Manage.JWRMD5, 119(6), 611–627.
Smith, J. A. (1988). “A model of daily municipal water use for short-term forecasting.” Water Resour. Res.WRERAQ, 24(2), 201–206.
Tang, Z., and Fishwick, P. A. (1993). “Feedforward neural nets as models for time series forecasting.” ORSA J. Comput.OJCOE3, 5(4), 374–385.
Valdes, J. B., and Sastri, T. (1989). “Rainfall intervention analysis for on-line applications.” J. Water Resour. Plann. Manage.JWRMD5, 115(4), 397–415.
Zahed, K. F. (1990). “Previsão de demanda de consumo em tempo real no desenvolvimento operacional de sistemas de distribuição de água.” Tese de doutorado, Escola Politécnica da Universidade de São Paulo, São Paulo.
Zhang, G. (2001). “An investigation of neural networks for linear time-series forecasting.” Comput. Oper. Res.69DGXP, 28(12), 1183–1202.
Zhang, G. P. (2003). “Time series forecasting using a hybrid ARIMA and neural network model.” Neurocomputing; Variable Star Bull.NRCGEO, 50, 159–175.
Zhang, J., Song, R., Bhaskar, N. R., and French, M. N. (2006). “Short-term water demand forecasting: A case study.” Proc., 8th Annual Water Distribution Systems Analysis Symp., ASCE, Reston, VA, 1–14.
Information & Authors
Information
Published In
Journal of Water Resources Planning and Management
Volume 138 • Issue 3 • May 2012
Pages: 245 - 256
Copyright
© 2012. American Society of Civil Engineers.
History
Received: Jun 7, 2010
Accepted: Aug 4, 2011
Published online: Apr 16, 2012
Published in print: May 1, 2012
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.