Open AccessArtificial Neural Networks for Urban Water Demand Forecasting: A Case Study
Author(s) -
Leandro L. Lorente-Leyva,
Jairo F Pavón-Valencia,
Yakcleem Montero-Santos,
Israel David Herrera-Granda,
Erick P. Herrera-Granda,
Diego H. Peluffo-Ordóñez
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1284/1/012004
Subject(s) - artificial neural network , demand forecasting , computer science , matlab , process (computing) , supply and demand , service (business) , set (abstract data type) , time series , water supply , operations research , data set , industrial engineering , artificial intelligence , machine learning , engineering , programming language , economy , environmental engineering , economics , microeconomics , operating system
This paper presents an application of an artificial neural network model in forecasting urban water demand using MATLAB software. Considering that in any planning process, the demand forecast plays a fundamental role, being one of the premises to organize and control a set of activities or processes. The versatility of the short, medium and long-term prediction that is provided to the company that offers the water distribution service to determine the supply capacity, maintenance activities, and system improvements as a strategic planning tool. Shown to improve network performance by using time series water demand data, the model can provide excellent fit and forecast without relying on the explicit inclusion of climatic factors and number of consumers. The excellent accuracy of the model indicates the effectiveness of forecasting over different time horizons. Finally, the results obtained from the Artificial Neural Network are compared with traditional statistical models.