Both planning and the design of water supply systems require accurate and reliable prediction of water demand. In this study, artificial neural network (ANN) was used to predict the long-term water demand to determine the relationship between dependent and independent parameters. Using the stationary chain to solve the interpolating characteristic of ANNs, the study presents a reliable approach for long-term forecasting of water demand. The purpose of this study is to provide a convenient and reliable method for long-term forecasting of urban water demand while reducing the prediction uncertainty. In order to evaluate the accuracy of the prediction, multilayer perceptron (MLP) outputs were compared with results from the linear regression model. Findings indicate that MLP is an appropriate solution for monthly long-term water demand forecasting. Furthermore, it can reduce uncertainties and significantly increase the accuracy of the long-term forecasting.
A long-term prediction of domestic water demand using preprocessing in artificial neural network
Sadegh Behboudian, Massoud Tabesh, Maliheh Falahnezhad, Farrokh Alavian Ghavanini; A long-term prediction of domestic water demand using preprocessing in artificial neural network. Journal of Water Supply: Research and Technology-Aqua 1 February 2014; 63 (1): 31–42. doi: https://doi.org/10.2166/aqua.2013.085
Download citation file: