Application of data prediction models in a real water supply network: comparison between arima and artificial neural networks

Abstract

Abstract Research around the world has focused on developing ways to predict hydraulic parameters in water distribution systems. The application of these forecasts can contribute to the decision-making of water distribution systems managers, aiming to ensure that the demand is met, and even to reduce water losses. The present work sought, among two data prediction models (ARIMA and Multi-Layer Perceptron Artificial Neural Networks), to assess which one can perform best predictions of pressure and discharge rate data. To reach the stipulated goal, real data were obtained from a water supply network provided by NUMMARH - Nucleus of Modeling and Simulation in Environment and Water Resources and Systems of the Federal University of Itajubá, Brazil. These data initially underwent an adjustment so that it was possible to develop a computer program. The results showed that the best prediction model for the data in question was ARIMA, presenting a mean absolute percentage error (MAPE) of 8.54%. Thus, it is concluded that ARIMA models are easy to build and apply, being an advantageous tool to predict such hydraulic parameters.