Forecasting Daily Urban Water Demand Using Artificial Neural Networks Based on Evolutionary Algorithms, A Case Study of Soufiyan Urban Water

Document Type : Original Article

Authors

1 Department of Civil Engineering, Azarbaijan Shahid Madani University, Tabriz, Iran

2 Professor, Faculty of Civil Engineering, University of Tabriz

3 PhD Student of Hydraulic Structure, Faculty of Civil Engineering, University of Tabriz

Abstract

Forecasting of water demand in water supply systems is essential to water resources management and its distribution as properly. According to non-linear and oscillation process of water consumption and its affecting variables, the use of non-linear models such as neural networks have get more success in this field. On the other hand, these models have some defects such as the need to more training data and weakness in finding global optimal solutions. In this study by combining the multi-layer neural networks with PSO and ICA evolutionary algorithms, the mentioned defects eliminated firstly, and then the neural networks trained and the daily water demand of Soufiyan city is predicted based on weather parameters. The results show that the hybrid neural network with PSO and ICA algorithms had better performance compared to a network that trained by LM classical algorithm. The hybrid model of neural network with PSO algorithm has correlation coefficient equal to 0.98 which have the more accurate solutions than other models in any of the warm and cold seasons. Also water demand forecasting with proposed hybrid model in the next 10 years revealed that water demand will be increased about 40% in this city.

Keywords


تابش،م.، دینی،م.، خوش­خلق،ع.ج.، زهرایی،ب. 1387. برآورد مصرف روزانه آب تهران با استفاده از سری­های زمانی، نشریه تحقیقات منابع آب ایران، 4. 2: 57-65.
سهرابی وفا،ح.، نوری،ف و عبادی،م. 1392. پیش­بینی تقاضای انرژی با استفاده از شبکه عصبی مبتنی بر الگوریتم انبوه ذرات، نشریه انرژی ایران، 16.3: 90-69.
Adamowski,J. 2008. Peak daily water demand forecast modeling using artificial neural networks. Journal of Water Resources Planning and Management. 134.2: 119-128.
Adamowski,J., Chan,H., Prasher,S., Ozga-Zielinski,B and Sliusarieva,A. 2012. Comparison of multiple linear and nonlinear regressions, autoregressive integrated moving average, artificial neural network, and wavelet artificial neural network methods for urban water demand forecasting in Montreal, Canada. Journal of Water Resources Research. 48.1: 1-14.
Ahmadi,M.A. 2011. Prediction of Asphatene precipitation using artificial neural network optimized by imperialist competitive algorithm, Journal of Petroleum Exploration and Production Technology, 1: 99-106.
Almutaz,I., Ajbar,A., Khalid,Y and Ali,E. 2012a. A probabilistic forecast of water demand for a tourist and desalination dependent city: case of Mecca, Saudi Arabia. Journal of Desalination. 294: 53-59.
Almutaz,I., Ajbar,A., Khalid,Y and Ali,E. 2012b. Determinants of residential water demand in an arid and oil rich country: a case study of Riyadh city in Saudi Arabia. International Journal of Physical Sciences, 7.43: 5787-5796.
Al-Zahrani,M and Abo-Monasar,A. 2015. Urban residential water demand prediction based on artificial neural networks and time Series Models. Journal of Water Resources Management. 29.10: 3651-3662.
Atashpaz-Gargari,E and Lucas,C. 2007. Imperialist competitive algorithm: an algorithm for optimization inspired by imperialistic competition. In: IEEE Congress on Evolutionary Computation, 25-28 September, (pp. 4661-4667). Suntec Singapore Intl. Convention & Exhibition Ctr, Singapore: IEEE.
Babel,M.S and Shinde,R.V. 2011. Identifying prominent explanatory variables for Water demand prediction using artificial neural networks: a case study of bangkok. Water Resources Management. 25. 1653-1676.
Bakker,M., Van Duist,H., Van Schagen,K., Vreeburg,J and Rietveld,L. 2014. Improving the performance of water demand forecasting models by using weather input. Journal of Procedia Engineering. 70: 93-102.
Chau,K.W. 2006. Particle swarm optimization training algorithm for ANNs in stage prediction of Shingmun river. Journal of Hydrology, 329.3-4: 363-367.
Chen,X. 2009. Prediction of urban water demand based on GA-SVM. International Conference on Future Computer and Communication. 6-7 June, (pp. 285-288). Huaiyin Institute of Technology Huaian, China: IEEE.
Ghiassi,G.A., Zimbra,D.K.B and Saidane,H.C. 2008. Urban water demand forecasting with a dynamic artificial neural network model. Journal of Water Resources Planning and Management, 134.2: 138-146.
Hornik,K. 1991. Approximation capabilities of multilayer feedforward networks. Journal of Neural Networks, 4: 251-257.
Kennedy,J and Eberhart,R. 1995. Particle swarm optimization. In: IEEE International Conference on Neural Networks, 25-28 September, (pp. 1942-1948). Perth, WA, Australia: IEEE.
Kennedy,J and Mendes,R. 2002. Population structure and particle swarm performance. In: IEEE Congr. Evol. Comput., 12-17 May.1671-1676.
Kim,J.H., Hwang,S.H and Shin,H.S. 2001. A neuro-genetic approach for daily water demand. Journal of Civil Engineering. 5.3: 281-288.
Kuok,K.K., Harun,S and Shamsuddin,S.M. 2010. Particle swarm optimization feed forward neural network for modeling run-off. International Journal of Environmental Science Technology. 7.1: 67-78.
Levenberg,k. 1944. A method for solution of certain non-linear problems in least squares. Journal of Quarterly of Applied Mathematics. 2: 164-168.
Lourakis,M. 2005. A brief description of the Levenberg-Marquardt algorithm implemented by levmar, Foundation for Research and Technology – Hellas: 1-7.
Marquardt,D. 1963. An algorithm for least-squares estimation of nonlinear parameters. SIAM Journal on Applied Mathematics. 11.2: 431-441.
McCulloch,W.S and Pitts,W. 1943. A logic calculus of the ideas immanent in nervous activity. Journal of Bulletin of Mathematical Biophysics. 5.4: 115-133.
McClelland,J.L., Rumelhart,D.E and Hinton,G.E. 1986. The appeal of distributed processing. In: Parallel Distributed Processing: Explorations in Microstructure of Cognition-Foundations. 1: 3-44.
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, 12-17 August, (pp. 13-18). Orlando, Florida: IEEE.
Sozen,A and Arcaklioglu,E. 2007. Prospects for Future Projections of the Basic Energy Sources in Turkey. Energy Sources, Part B: Economics, Planning, and Policy. 2:183-201.
Tabesh,M., Goosheh,S and Yazdanpanah,M.J. 2006. Short term water demand forecasting of Tehran city by artificial neural network. Journal of Tehran University Engineering Faculty. 41.2: 11-24.
Tabesh,M and Dini,M. 2008. Fuzzy and neuro- fuzzy models for short-term water demand forecasting in Tehran. Iranian Journal of Science and Technology, Transaction B, 33.1: 61-77.
Zhang,G., Patuwo,B.E and Hu,M. 1998. Forecasting with artificial neural network: the state of art. International Journal of Forecasting. 14.1: 35-62.