Hybrid Water Demand Forecasting Model Associating Artificial Neural Network with Fourier Series

This paper addresses 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, Sao Paulo, Brazil. Like most recent research, it uses Artificial Neural Networks (ANNs) 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 Backpropagation algorithm (MLP-BP), the Dynamic Neural Network (DAN2) and two hybrid ANNs. The hybrid models use the error produced by the Fourier series forecasting as input to the MLP-BP and DAN2, called respectively ANN-H and DAN2-H. Other inputs, such as the demand and weather variables (temperature and humidity) were selected based on autocorrelation and correlation analysis, respectively. The results are promising with the hybrid models in general performing better than the usual ANN models. DAN2-H, identified as the best model, produced a Mean Absolute Error of 2.25 L/s and 2.06 L/s for training and test set respectively, which represent about 8% of the average consumption.

[1]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[2]  Shin Ishii,et al.  A Bayesian missing value estimation method for gene expression profile data , 2003, Bioinform..

[3]  Paul A. Fishwick,et al.  Feedforward Neural Nets as Models for Time Series Forecasting , 1993, INFORMS J. Comput..

[4]  K. Adamowski,et al.  Short‐term municipal water demand forecasting , 2005 .

[5]  E. D. Farmer,et al.  Development of online load-prediction techniques with results from trials in the south-west region of the CEGB , 1968 .

[6]  J. Smith,et al.  A model of daily municipal water use for short‐term forecasting , 1988 .

[7]  Patrick F. Perry.  Demand Forecasting in Water Supply Networks , 1981 .

[8]  Ashu Jain,et al.  Short‐term water demand forecast modeling techniques—CONVENTIONAL METHODS VERSUS AI , 2002 .

[9]  Pericles A. Mitkas,et al.  A Hybrid Agent-Based Model for Estimating Residential Water Demand , 2005, Simul..

[10]  Guoqiang Peter Zhang,et al.  An investigation of neural networks for linear time-series forecasting , 2001, Comput. Oper. Res..

[11]  Chengchao Xu,et al.  DEMAND FORECASTING FOR WATER DISTRIBUTION SYSTEMS , 1992 .

[12]  Raymond L. Anderson,et al.  WATER SAVINGS FROM LAWN WATERING RESTRICTIONS DURING A DROUGHT YEAR, FORT COLLINS, COLORADO , 1980 .

[13]  J. Nazuno.  Haykin, Simon. Neural networks: A comprehensive foundation, Prentice Hall, Inc. Segunda Edición, 1999 , 2000 .

[14]  David Zimbra,et al.  Urban Water Demand Forecasting with a Dynamic Artificial Neural Network Model , 2008 .

[15]  Ashu Jain,et al.  Hybrid neural network models for hydrologic time series forecasting , 2007, Appl. Soft Comput..

[16]  Eng Aik Lim,et al.  A comparative study of missing value estimation methods: Which method performs better? , 2008, 2008 International Conference on Electronic Design.

[17]  H. Yamauchi,et al.  WRRCTR No. 84 An economic analysis of the patterns and trends of water consumption within the service areas of the Honolulu Board of Water Supply. , 1974 .

[18]  Manoochehr Ghiassi,et al.  A dynamic architecture for artificial neural networks , 2005, Neurocomputing.

[19]  Uri Shamir,et al.  Forecasting Hourly Water Demands by Pattern Recognition Approach , 1993 .

[20]  J. Adamowski.  Peak Daily Water Demand Forecast Modeling Using Artificial Neural Networks , 2008 .

[21]  H. A. Dryar,et al.  The Effect of Weather on the System Load , 1944, Transactions of the American Institute of Electrical Engineers.

[22]  Ashu Jain,et al.  Short-Term Water Demand Forecast Modelling at IIT Kanpur Using Artificial Neural Networks , 2001 .

[23]  Shaw-Pin Miaou,et al.  A class of time series urban water demand models with nonlinear climatic effects , 1990 .

[24]  David R. Maidment,et al.  Transfer Function Models of Daily Urban Water Use , 1985 .

[25]  Juan B. Valdés,et al.  Rainfall Intervention Analysis for On‐Line Applications , 1989 .

[26]  Guoqiang Peter Zhang,et al.  Time series forecasting using a hybrid ARIMA and neural network model , 2003, Neurocomputing.

[27]  Luisa Fernanda Ribeiro Reis,et al.  Análise comparativa dos modelos kNN-TSP e série de Fourier para previsão de demanda horária para abastecimento de água , 2009 .

[28]  Charles W. Howe,et al.  The impact of price on residential water demand and its relation to system design and price structure , 1967 .

[29]  Kamel Zahed Filho.  Previsão de demanda de consumo em tempo real no desenvolvimento operacional de sistemas de distribuição de água. , 1990 .

[30]  N. Bhaskar,et al.  SHORT-TERM WATER DEMAND FORECASTING: A CASE STUDY , 2008 .

[31]  Inmaculada Pulido-Calvo,et al.  Improved irrigation water demand forecasting using a soft-computing hybrid model , 2009 .

[32]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.