An optimal neural network model for daily water demand forecasting

Joong Hoon Kim, Seok H. Hwang, Hyun S. Shin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

An optimal neural network model for daily water demand forecasting is presented. It has been reported that variation of water demand is related to the weather. A number of researches have shown that the relationships between daily water demand and exogenous variables usually are nonlinear. However, the majority of the short-term water demand forecasting models published have treated the daily water demands as a stochastic time series, and described the relationships by using linear expressions. This study tackles the complexity of the relationship between daily water demands and exogenous variables. In an effort to more effectively forecast the daily water demands, a neuro-genetic algorithm is adopted in this study, which is a combination of the Neural network and the Genetic algorithm. Temperatures, previous day's water demand, sunshine-duration period, and day type have significant impact on the daily water demand forecasting. If only one input parameter is to be used, a model which uses previous day's water demand as an input parameter shows the best results. Among all the models tested in this study, a neuro-genetic model with input parameters of two previous days' demands and today's and yesterday's average temperatures shows the best performance in today's water demand forecasting. It is recommended that a number of models with various input parameters be tested before any particular model is adopted for a specific service area.

Original languageEnglish
Title of host publicationWRPMD 1999: Preparing for the 21st Century
PublisherAmerican Society of Civil Engineers (ASCE)
ISBN (Print)0784404305, 9780784404300
DOIs
Publication statusPublished - 1999
Event29th Annual Water Resources Planning and Management Conference, WRPMD 1999 - Tempe, AZ, United States
Duration: 1999 Jun 61999 Jun 9

Other

Other29th Annual Water Resources Planning and Management Conference, WRPMD 1999
CountryUnited States
CityTempe, AZ
Period99/6/699/6/9

Fingerprint

Neural networks
Water
Genetic algorithms
Time series
Temperature

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Kim, J. H., Hwang, S. H., & Shin, H. S. (1999). An optimal neural network model for daily water demand forecasting. In WRPMD 1999: Preparing for the 21st Century American Society of Civil Engineers (ASCE). https://doi.org/10.1061/40430(1999)236

An optimal neural network model for daily water demand forecasting. / Kim, Joong Hoon; Hwang, Seok H.; Shin, Hyun S.

WRPMD 1999: Preparing for the 21st Century. American Society of Civil Engineers (ASCE), 1999.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kim, JH, Hwang, SH & Shin, HS 1999, An optimal neural network model for daily water demand forecasting. in WRPMD 1999: Preparing for the 21st Century. American Society of Civil Engineers (ASCE), 29th Annual Water Resources Planning and Management Conference, WRPMD 1999, Tempe, AZ, United States, 99/6/6. https://doi.org/10.1061/40430(1999)236
Kim JH, Hwang SH, Shin HS. An optimal neural network model for daily water demand forecasting. In WRPMD 1999: Preparing for the 21st Century. American Society of Civil Engineers (ASCE). 1999 https://doi.org/10.1061/40430(1999)236
Kim, Joong Hoon ; Hwang, Seok H. ; Shin, Hyun S. / An optimal neural network model for daily water demand forecasting. WRPMD 1999: Preparing for the 21st Century. American Society of Civil Engineers (ASCE), 1999.
@inproceedings{8e1e2689cdcf4b35b6fd0d4b1dccde37,
title = "An optimal neural network model for daily water demand forecasting",
abstract = "An optimal neural network model for daily water demand forecasting is presented. It has been reported that variation of water demand is related to the weather. A number of researches have shown that the relationships between daily water demand and exogenous variables usually are nonlinear. However, the majority of the short-term water demand forecasting models published have treated the daily water demands as a stochastic time series, and described the relationships by using linear expressions. This study tackles the complexity of the relationship between daily water demands and exogenous variables. In an effort to more effectively forecast the daily water demands, a neuro-genetic algorithm is adopted in this study, which is a combination of the Neural network and the Genetic algorithm. Temperatures, previous day's water demand, sunshine-duration period, and day type have significant impact on the daily water demand forecasting. If only one input parameter is to be used, a model which uses previous day's water demand as an input parameter shows the best results. Among all the models tested in this study, a neuro-genetic model with input parameters of two previous days' demands and today's and yesterday's average temperatures shows the best performance in today's water demand forecasting. It is recommended that a number of models with various input parameters be tested before any particular model is adopted for a specific service area.",
author = "Kim, {Joong Hoon} and Hwang, {Seok H.} and Shin, {Hyun S.}",
year = "1999",
doi = "10.1061/40430(1999)236",
language = "English",
isbn = "0784404305",
booktitle = "WRPMD 1999: Preparing for the 21st Century",
publisher = "American Society of Civil Engineers (ASCE)",

}

TY - GEN

T1 - An optimal neural network model for daily water demand forecasting

AU - Kim, Joong Hoon

AU - Hwang, Seok H.

AU - Shin, Hyun S.

PY - 1999

Y1 - 1999

N2 - An optimal neural network model for daily water demand forecasting is presented. It has been reported that variation of water demand is related to the weather. A number of researches have shown that the relationships between daily water demand and exogenous variables usually are nonlinear. However, the majority of the short-term water demand forecasting models published have treated the daily water demands as a stochastic time series, and described the relationships by using linear expressions. This study tackles the complexity of the relationship between daily water demands and exogenous variables. In an effort to more effectively forecast the daily water demands, a neuro-genetic algorithm is adopted in this study, which is a combination of the Neural network and the Genetic algorithm. Temperatures, previous day's water demand, sunshine-duration period, and day type have significant impact on the daily water demand forecasting. If only one input parameter is to be used, a model which uses previous day's water demand as an input parameter shows the best results. Among all the models tested in this study, a neuro-genetic model with input parameters of two previous days' demands and today's and yesterday's average temperatures shows the best performance in today's water demand forecasting. It is recommended that a number of models with various input parameters be tested before any particular model is adopted for a specific service area.

AB - An optimal neural network model for daily water demand forecasting is presented. It has been reported that variation of water demand is related to the weather. A number of researches have shown that the relationships between daily water demand and exogenous variables usually are nonlinear. However, the majority of the short-term water demand forecasting models published have treated the daily water demands as a stochastic time series, and described the relationships by using linear expressions. This study tackles the complexity of the relationship between daily water demands and exogenous variables. In an effort to more effectively forecast the daily water demands, a neuro-genetic algorithm is adopted in this study, which is a combination of the Neural network and the Genetic algorithm. Temperatures, previous day's water demand, sunshine-duration period, and day type have significant impact on the daily water demand forecasting. If only one input parameter is to be used, a model which uses previous day's water demand as an input parameter shows the best results. Among all the models tested in this study, a neuro-genetic model with input parameters of two previous days' demands and today's and yesterday's average temperatures shows the best performance in today's water demand forecasting. It is recommended that a number of models with various input parameters be tested before any particular model is adopted for a specific service area.

UR - http://www.scopus.com/inward/record.url?scp=84904690324&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84904690324&partnerID=8YFLogxK

U2 - 10.1061/40430(1999)236

DO - 10.1061/40430(1999)236

M3 - Conference contribution

AN - SCOPUS:84904690324

SN - 0784404305

SN - 9780784404300

BT - WRPMD 1999: Preparing for the 21st Century

PB - American Society of Civil Engineers (ASCE)

ER -