Prediction of Minimum Night Flow for Enhancing Leakage Detection Capabilities in Water Distribution Networks

Abstract

In South Korea, a water supply enhancement project is being carried out to preemptively respond to drought and water loss by reducing pipeline leakages and supplying stable tap water through the maintenance of an aging water supply network. In order to reduce water leakage, a District Metered Area (DMA) was established to monitor and predict the minimum night flow based on flow data collected from IoT sensors. In this study, a model based on Multi-Layer Perceptron (MLP) and Long Short-Term Memory (LSTM) was constructed to predict the MNF (minimum night flow) of County Y. The prediction of MNF results was compared with the MLP networks and the LSTM model. The outcome showed that the LSTM-MNF model proposed in this study performed better than the MLP-MNF model. Therefore, the research methods of this study can contribute to technical support for leakage reductions by preemptively responding to the expected increase in leakage through the prediction of the minimum flow at night.