Water demand forecasting using machine learning
Janusz Łomotowski
Joanna Kajewska-Szkudlarek
Justyna Stańczyk
Paweł Rychlikowski
Piotr Lipiński
Tomasz Konieczny
  
Keywords: machine learning, water consumption prediction, meteorological parameters, water systems, computational intelligence

 
Summary
Predicting water consumption is an important issue at the stage of water systems operation. In recent years, some numerical
WDF (Water Demand Forecasting) water consumption prediction systems have been created, which allow to foresee
consumption rates for short, medium and long terms. The forecasts support decision-making process concerning the
design, expansion and maintenance of water systems and the implementation of procedures optimizing the operation of
pumping stations, water treatment and sewage treatment plants.
The article describes the use of computational intelligence and machine learning to predict water demand rates. The results
of a forecast prepared with the use of nonlinear regression based on Support Vector Regression (SVR) with kernel functions
defined by Radial Basis Functions (RBF) are presented. The influence of weather situation on water consumption rates for
two District Metered Areas (DMA) in Wrocław, each with different land development conditions, was analysed. It was proved
that it is advisable to take the maximum daily temperature into account while estimating water demand rates. It was shown
that skipping trends and seasonality in measuring data allows to create better prediction models.
The water consumption prediction model presented may be regarded as one of the tools facilitating decision-making processes
at management and water system utilisation levels.
 

Redakcja GAZ WODA I TECHNIKA SANITARNA
Siedziba redakcji: ul. Czackiego 3/5, pok.404, 00-043 Warszawa
tel./fax 0 22 827 02 49 tel. 22 336 14 07, www.gazwoda.pl
e-mail: gwits@poczta.onet.pl, gazwoda@sigma-not.pl

Wydawnictwo SIGMA-NOT Sp. z o.o.
ul. Ratuszowa 11, 00-950 Warszawa, skr. poczt. 1004
Sąd Rejonowy dla m.st. Warszawy, XIII Wydział Gospodarczy, KRS: 0000069968
NIP
: 524 030 35 01
Kapitał zakładowy: 752 361,80 zł 

Na naszej witrynie wykorzystujemy pliki cookies w celu realizacji usług oraz gromadzenia informacji związanych z korzystaniem ze strony.

Plikami cookies możesz zarządzać w opcjach przeglądarki, z której korzystasz. Więcej informacji znajdziesz tutaj.