Assessment of predictive models for estimation of water consumption in public preschool buildings

Abstract

Preschool buildings are among the biggest water consumers in the public buildings sector, which efficient management of water consumption could make considerable savings in city budgets. The aim of this study was twofold: 1) to assess prognostic performances of 21 parameters that influence the water consumption and 2) to assess performances of two different approaches (statistical and machine learning-based) with 6 various predictive models for the estimation of water consumption by using the observed parameters. The considered data set was collected from the total share of public preschool buildings in the city of Kragujevac, Serbia, over a three-year period. The top-performing statistical-based model was Multiple linear regression (MLR), while the best machine learning method was Random Forest (RF). Particularly, RF gained the best overall performances R²=0.90 (2% better than the MLR), while the MLR showed the same MAPE precision as the RF when dealing with buildings that consume more than 200 m³/month. It is found that both MLR and RF provide satisfying estimates, leaving for potential users to choose between better performances (RF) or usability (MLR).