Forecasting water consumption in towns of different sizes

Abstract

The aim of the work was to compare water consumption forecasting in two towns of different sizes. The objects of research were the town of Toruń and the town of Żnin in central Poland. Two models were built for each. The models were constructed using the multiple regression method. In constructing the models, explanatory variables determined by Principal Component Analysis (PCA) were used. The set of explanatory variables identified to construct each individual model differed. The models for Toruń obtained better forecast quality assessment criteria values. This was mainly due to the water supply system in the small town (Żnin) being less resilient to sudden, short-term changes in consumers’ water use. At the same time, the importance of the location of the meteorological stations from which data was taken to build the model was emphasised.