Authors: B. Coelho; A. Gil Andrade-Campos
Addresses: Department of Mechanical Engineering, Centre for Mechanical Technology and Automation, GRIDS Research Group, University of Aveiro, Campus Universitário de Santiago, 3810-193 Aveiro, Portugal ' Department of Mechanical Engineering, Centre for Mechanical Technology and Automation, GRIDS Research Group, University of Aveiro, Campus Universitário de Santiago, 3810-193 Aveiro, Portugal
Abstract: Predicting future water demands is becoming essential for the efficient management of water supply systems (WSS). To improve the operations of a Portuguese network, short-term water demand forecasting models are applied to a number of datasets collected from distinct locations in the network. Traditional forecasting models, such as exponential smoothing and naïve models, and artificial neural network (ANN)-based models are developed and compared. Additionally, the influence of anthropic and weather variables in the ANN-based models is also analysed. Results demonstrate that, for this case-study, ANN-based models outperform the traditional models when external predictors such as anthropic and weather variables are included in the models. However, the inappropriate choice of such variables may lead to worse forecasting performances.
Keywords: water demand forecasting; artificial neural networks; ANN; data analysis; exponential smoothing; naïve methods; Portuguese water network; short-term forecasting; water supply and distribution systems.
International Journal of Water, 2019 Vol.13 No.2, pp.173 - 207
Available online: 02 May 2019 *Full-text access for editors Access for subscribers Purchase this article Comment on this article