Short-term water demand predictions coupling an artificial neural network model and a genetic algorithm

Abstract

The application of artificial neural network (ANN) models for short-term (15 min) urban water demand predictions is evaluated. Optimization of the ANN model's hyperparameters with a genetic algorithm (GA) and use of a growing window approach for training the model are also evaluated. The results are compared to those of commonly used time series models, namely the Autoregressive Integrated Moving Average (ARIMA) model and a pattern-based model. The evaluations are based on data sets from two Canadian cities, providing 15 min water consumption records over respectively 5 years and 23 months, with a respective mean water demand of 14,560 and 887 m3/d. The GA optimized ANN model performed better than the other models, with Nash–Sutcliffe Efficiencies of 0.91 and 0.83, and relative root mean square errors of 6 and 16% for City 1 and City 2, respectively. The results of this study indicate that the optimization of the hyperparameters of an ANN model can lead to better 15 min urban water demand predictions, which are useful for many real-time control applications, such as dynamic pressure control. HIGHLIGHTS ANN models were used for short-term (15 min) urban water demand predictions.; The hyperparameters of the ANN model were optimized with a genetic algorithm for better model performance.; The results of the ANN approach were compared to an ARIMA and a pattern-based models for two different datasets.; The performance results proved GA optimized ANN model as an efficient approach for short-term UWD predictions.;

Keywords

• artificial neural network
• genetic algorithm
• hyperparameter optimization
• short term
• time series model
• urban water demand prediction