Next Article in Journal
Visual Investigation of the Occurrence Characteristics of Multi-Type Formation Water in a Fracture–Cavity Carbonate Gas Reservoir
Next Article in Special Issue
Economic Model Predictive Control with Nonlinear Constraint Relaxation for the Operational Management of Water Distribution Networks
Previous Article in Journal
Flashover Performance Test with Lightning Impulse and Simulation Analysis of Different Insulators in a 110 kV Double-Circuit Transmission Tower
Article Menu
Issue 3 (March) cover image

Export Article

Open AccessArticle
Energies 2018, 11(3), 660; https://doi.org/10.3390/en11030660

Multi-Model Prediction for Demand Forecast in Water Distribution Networks

1
CONACYT—Consorcio CENTROMET, Camino a Los Olvera 44, Los Olvera, Corregidora, Querétaro 76904, Mexico
2
Institut de Robótica i Informática Industrial (CSIC-UPC), Carrer LLorens Artigas 4-6, Barcelona 08028, Spain
3
División de Estudios de Posgrado e Investigación, Instituto Tecnológico de Culiacán, Juan de Dios Bátiz 310 pte, Culiacán 80220, Mexico
4
División de Estudios de Posgrado de la Facultad de Ingeniería Eléctrica, Universidad Michoacana de San Nicolás de Hidalgo, Gral. Francisco J. Múgica S/N, Morelia 58040, Mexico
These authors contributed equally to this work.
*
Author to whom correspondence should be addressed.
Received: 24 February 2018 / Revised: 11 March 2018 / Accepted: 13 March 2018 / Published: 15 March 2018
(This article belongs to the Special Issue Smart Water Networks in Urban Environments)
Full-Text   |   PDF [1953 KB, uploaded 15 March 2018]   |  

Abstract

This paper presents a multi-model predictor called Qualitative Multi-Model Predictor Plus (QMMP+) for demand forecast in water distribution networks. QMMP+ is based on the decomposition of the quantitative and qualitative information of the time-series. The quantitative component (i.e., the daily consumption prediction) is forecasted and the pattern mode estimated using a Nearest Neighbor (NN) classifier and a Calendar. The patterns are updated via a simple Moving Average scheme. The NN classifier and the Calendar are executed simultaneously every period and the most suited model for prediction is selected using a probabilistic approach. The proposed solution for water demand forecast is compared against Radial Basis Function Artificial Neural Networks (RBF-ANN), the statistical Autoregressive Integrated Moving Average (ARIMA), and Double Seasonal Holt-Winters (DSHW) approaches, providing the best results when applied to real demand of the Barcelona Water Distribution Network. QMMP+ has demonstrated that the special modelling treatment of water consumption patterns improves the forecasting accuracy. View Full-Text
Keywords: prediction; multi-model; water demand; short-term prediction prediction; multi-model; water demand; short-term prediction
Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).

Supplementary materials

  • Supplementary File 1:

    Supplementary (ZIP, 186 KB)

  • Externally hosted supplementary file 1
    Link: https://github.com/rdglpz/QMMP_EXPERIMENTS
    Description: IMPORTANT: This is the first time the codes and databases are uploaded with the aim to provide the experiments we report in this manuscript **README** Supplementary files of the manuscript "Multi-model Prediction for Demand Forecast in Water Distribution Networks". This folder contains the codes in MATLAB and R that generate the results presented in tables 1 to 5. for the manuscript. The folder demands2012 contains the water demand time series. The folder package_qmmp contains all the codes in .m required by the MATLAB main files. The "MATLAB_main01_QMM.m", "MATLAB_main02_ARIMA.m" and "MATLAB_main03_RBFANN.m" codes have been tested in MATLAB2017b 64-bit (win64). a) The "MATLAB_main01_QMMMP.m" generates: 1. The m', m and epsilon columns of Table 1. SARIMA coefficients for each time series. 2. The QMMP+, Cal, NN and Naive columns of Table 2 to 4 reporting MAE, RMSE and MAPE. 3. The mean of the individual variances (Table 5) of QMMP+, Cal, NN and Naive . b) The "MATLAB_main02_ARIMA.m" generates: 1. The ARIMA column results of Tables 2 to 4 reporting MAE, RMSE and MAPE. 2. The mean of the individual variances (Table 5) of ARIMA. c) The "MATLAB_main03_RBFANN.m" generates: 1. The RBFANN column results of Tables 2 to 4 reporting MAE, RMSE and MAPE. 3. The mean of the individual variances (Table 5) of RBFANN. The "R_main01_ DSHW.R" and "Autoarima.R" codes have been tested in R version 3.4.3 d) The "R_main01_ DSHW.R" generates the results: 1. The DSHW column results of Tables 2 to 4 reporting MAE, RMSE and MAPE. 2. The mean of the individual variances (Table 5) of DSHW. d) The "Autoarima.R" estimates the ARIMA coefficients used in "MATLAB_main02_ARIMA.m". -Rodrigo López-Farías [email protected]
SciFeed

Share & Cite This Article

MDPI and ACS Style

Lopez Farias, R.; Puig, V.; Rodriguez Rangel, H.; Flores, J.J. Multi-Model Prediction for Demand Forecast in Water Distribution Networks. Energies 2018, 11, 660.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Energies EISSN 1996-1073 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top