Forecasting Daily Urban Water Demand Using Artificial Neural Networks, A Case Study of Tehran Urban Water

Document Type : Research Paper

Authors

1 1. Assoc. Prof. and Member of the Center of Excellence on Infrastructure Engineering and Management, Dept. of Civil Engineering, Faculty of Engineering, University of Tehran

2 M.Sc. Graduate of Water Resources Engineering and Instructor of Azad University, Ahar Branch

Abstract

Water demand forecasting is one of the most important concerns for managers of water supply systems as the results can affect many decisions. Daily demand forecasting cannot be usually accomplished by mathematical functions because it is a complicated function of many variables. In this paper, neural networks are used to predict Tehran daily water demand. At first, weather data from three Tehran weather stations are weighted via the Thissen method and the effective input data parameters are selected using the regression of the weighted effective weather and consumption data. The effective parameters include daily average temperature, relative humidity, and last day to last week (7 days) as well as last year water consumptions. Three different ANN models are built in this stage: a three-layer model with one hidden layer including seven neurons, a four-layer model with two hidden layers including seven neurons in the first and four neurons in the second hidden layer, and a RBF three-layer model with twenty neurons in the middle layer. Comparison of the results of ANN with neuro-fuzzy and time series models shows that ANN models have a higher capability for predicting Tehran daily water consumption. Among these models, the ANN perceptron 3-layer model with a nonlinear output produced more accurate results.

Keywords


1- Zhou, S.L., Mcmohon, T.A., Walton, A., and Lewis, J. (2000). “Forecasting daily urban water demand: A case study of  Melborne.” J. Hydrology, 236, 153-164.
2- Zhou, S.L., Mcmohon, T.A., Walton, A., and Lewis, J. (2001). “Forecasting operation demand for an urban water supply zone.” J. Hydrology, 259, 189-202.
3- تابش، م.، دینی، م.، خوش خلق، ج.، و زهرایی، ب. (1387). برآورد مصرف کوتاه مدت آب شهری تهران با استفاده از سری‌های زمانی. م. تحقیقات منابع آب، 11 (2)، 57-65.
4- Bowden, G.J., Maier, H.R., and Dandy, G.C. (2002). “Optimal division of data for neural network models in water resources applications.” Water Resources Research, 38(2), 1-11.
5- Milot, J., Rodriguez, M.J., and Sérodes, J.B. (2002). “Contribution of neural networks for modeling trihalomethanes occurrence in drinking water.” J. of Water Resources Planning and Management, 128(5), 370-376,
6- Michaelides, S.C., Pattichis, C.S., and Kleovoulou, G. (2001). “Classification of rainfall variability by using artificial neural networks.” International J. of Climatology, 21, 1401-1414.
7- Stark, H.L., Stanley, S.J. and Buchanan, I.D. (2000). “The application of artificial neural networks to water demand modeling.” Annual Conference Abstracts of Canadian Society for Civil Engineering, 139
8-Jain, A., Joshi, U.C., and Varshney, A.K. (2000). “Short-term water demand forecasting using artificial neural networks: IIT Kanpur experience.” In Proceedings of International Conference on Pattern Recognition, 15(2),
459-462.
9- Jain, A., Varshney, A.K., and Joshi, U.C. (2001). “Short-term water demand forecast modeling at IIT Kanpur using artificial neural networks.” Water Resources Management, 15(5), 299-321.
10- Liu, J., Savenije, H.G., and Xu, J. (2003). “Forecast of water demand in Weinan City in China using WDF-ANN model.” Physics and Chemistry of the Earth, 28(4-5), 219-224
 11- Yu, T-C, Zhang, T. Q., Mao, G. H., and Wu, X, G. (2004). “Study of artificial neural network model for forecasting urban water demand.” J. of Zhejiang University (Engineering Science), 38(9), 1156-1161.
12- Bougadis, J., Adamowski, K.B., and  Diduch, R. (2005). “Short-term municipal water demand forecasting.” Hydrological Processes, 19(1), 137-148.
13- Adamowski, J.F. (2008). “Peak daily water demand forecast modeling using artificial neural networks.” J. of Water Resources Planning and Management, 134(2), 119-128.
14- Chang, N.B., and Makkeasorn, A. (2007). “Water demand analysis in urban region by neural network models.” In Proceedings of the 8th Annual Water Distribution Systems Analysis Symposium, 48.
15- Msiza, I.S., Nelwamondo, F.V., and Marwala, T. (2007). “Water demand forecasting using multi-layer perceptron and radial basis functions.” In Proceedings of the IEEE International Conference on Neural Networks, Article,
13-18.
16- Zhang, J., Song, R., Bhaskar, N. R., and French, M.N. (2007). “Short-term water demand forecasting: A case study.” In Proceedings of the 8th Annual Water Distribution Systems Analysis Symposium , 49.
17- Ghiassi, G. A, Zimbra, D. K. B., and Saidane, H.C. (2008). “Urban water demand forecasting with a dynamic artificial neural network model.” J. of Water Resources Planning and Management, 134(2), 138-146.
18-Yurdusev, M.A., Firat, M., Mermer, M., and Turan, M.E. (2009). “Water use prediction by radial and feed-forward neural nets.” In Proceedings of the Institution of Civil Engineers: Water Management, 162(3),  179-188.
19- کریمی، د. (1380). کاربرد منطق فازی در پیش‌بینی کوتاه مدت مصرف آب تهران. پایان نامه کارشناسی ارشد، گروه مهندسی عمران محیط زیست، دانشگاه تربیت مدرس، تهران.
20- تابش، م.، گوشه، س.، و یزدانپناه، م.ج. (1386). کاربرد شبکه‌های عصبی مصنوعی در تخمین تقاضای کوتاه مدت آب شهری. نشریه دانشکده فنی، 41(1)، 11-24.
21- Tabesh, M., and Dini, M. (2008). “Fuzzy and neuro- fuzzy models for short-term water demand forecasting in tehran.” Iranian J. of Science and Technology, Transaction B, 33 (1), 61-77.
22- Buchberger, G., and Wu, L. (1995). “Model for instantaneous residential water demand.” J. of Hydraulic Engineering, 121(3), 232-246.
23- Buchberger, G., and Wells, G.J. (1996). “Intensity, duration and frequency of residential water demands.” J. of Water Resources Planning and Management, 122(11), 11-18.
24- Haykin, S. (1999). Neural networks: a comprehensive foundation, Prentice Hall, New Jersey, USA.
25- Nelles, O. (2001). Nonlinear system identification, Springer Verlag, Berlin.
26- تابش، م. ( 1385). تخمین تقاضای کوتاه مدت آب شهری با استفاده از شبکه‌های عصبی و سیستم‌های فازی و ترکیبی، گزارش نهایی طرح پژوهشی، مؤسسه آب دانشگاه تهران، انتشارات شرکت مدیریت منابع آب ایران، وزارت نیرو، تهران.