Short‐term water demand forecast modeling techniques—CONVENTIONAL METHODS VERSUS AI

Jain, Ashu; Ormsbee, Lindell

doi:10.1002/j.1551-8833.2002.tb09507.x

Cited by 134 publications

(81 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, the nonlinearity degrees of water demand data vary greatly, making the linear methods unable to handle adequately. In this scenario, nonlinear methods such as ANNs function to improve the performance of forecasting, and it has been found that ANN models perform better than regression and univariate time series analysis [13,16,17].…”

Section: Introduction Wmentioning

confidence: 99%

City Water Demand Forecasting Based on Improved BP Neural Network

Xing¹,

You²,

Zhang³

et al. 2017

JRST

View full text Add to dashboard Cite

City water demand forecasting is of great significance in reducing the cost of electricity consumption and municipal planning. Back-propagation (BP) neural network has been widely adopted in water demand forecasting in recent years. But BP performs unsatisfactorily in terms of training time and global searching ability, so in this paper we improve BP by two heuristic algorithms, namely, genetic algorithm (ga) and particle swarm optimization (PSO), respectively. The testing and verification of the three algorithms (BP, ga+BP, PSo+BP) have been conducted on real-life water demand forecasting of Beijing city. The obtained results demonstrate that, in spite of the execution time consumed, both ga+BP and PSo+BP performed with higher accuracy and less errors than BP. The obtained results also illustrate that PSo+BP slightly outperformed ga+BP in terms of forecasting accuracy.

show abstract

Section: Introduction Wmentioning

confidence: 99%

City Water Demand Forecasting Based on Improved BP Neural Network

Xing¹,

You²,

Zhang³

et al. 2017

JRST

View full text Add to dashboard Cite

show abstract

“…Furthermore, multiple-scale interactions between individuals and natural systems create a further range of urban water demand management challenges [HOUSE-PETERS, CHANG 2011]. Short-term urban water de-mand forecasts play a significant role in the optimal operation of pumps, wells, and reservoirs, as well as in informing decisions regarding balanced water resource allocation in the face of urgent water needs [HERRERA et al 2010;JAIN, ORMSBEE 2002;KAME'ENUI 2003]. Urban water is generally allocated according to the experience of operators and average water demand; however, accurate and reliable forecasts of short-term demand can help operators provide water in a more efficient and sustainable manner [ZHOU et al 2002].…”

Section: Introductionmentioning

confidence: 99%

Water demand forecasting using extreme learning machines

Tiwari¹,

Adamowski²,

Adamowski³

2016

Journal of Water and Land Development

View full text Add to dashboard Cite

The capacity of recently-developed extreme learning machine (ELM) modelling approaches in forecasting daily urban water demand from limited data, alone or in concert with wavelet analysis (W) or bootstrap (B) methods (i.e., ELM, ELM W , ELM B ), was assessed, and compared to that of equivalent traditional artificial neural network-based models (i.e., ANN, ANN W , ANN B ). The urban water demand forecasting models were developed using 3-year water demand and climate datasets for the city of Calgary, Alberta, Canada. While the hybrid ELM B and ANN B models provided satisfactory 1-day lead-time forecasts of similar accuracy, the ANN W and ELM W models provided greater accuracy, with the ELM W model outperforming the ANN W model. Significant improvement in peak urban water demand prediction was only achieved with the ELM W model. The superiority of the ELM W model over both the ANN W or ANN B models demonstrated the significant role of wavelet transformation in improving the overall performance of the urban water demand model.

show abstract

“…They observed that the ANN presented results at least comparable with those from statistical methods. Jain et al (2001); Jain and Ormsbee (2002);and Bougadis et al (2005) concluded that the ANN performs better than regression and time-series analysis. Jain et al (2001) observed during the investigation of the inputs for the ANN that meteorological factors have significant influence on the short-term forecast, especially the air temperature and the occurrence of rainfall, the latter being more significant than the amount of rain itself.…”

Section: Introductionmentioning

confidence: 99%

“…Jain et al (2001) observed during the investigation of the inputs for the ANN that meteorological factors have significant influence on the short-term forecast, especially the air temperature and the occurrence of rainfall, the latter being more significant than the amount of rain itself. The ANN model developed by Jain and Ormsbee (2002) for daily water demand was a function of the daily water consumption from the previous day and the daily maximum air temperature of the current day. Bougadis et al (2005), unlike Jain et al (2001), found that water demand on a weekly basis was better correlated with the rainfall amount than the occurrence of rainfall.…”

Section: Introductionmentioning

confidence: 99%

Hybrid Water Demand Forecasting Model Associating Artificial Neural Network with Fourier Series

Odan

Reis

2012

J. Water Resour. Plann. Manage.

View full text Add to dashboard Cite

This paper addressed the problem of water-demand forecasting for real-time operation of water supply systems. The present study was conducted to identify the best fit model using hourly consumption data from the water supply system of Araraquara, São Paulo, Brazil. Artificial neural networks (ANNs) were used in view of their enhanced capability to match or even improve on the regression model forecasts. The ANNs used were the multilayer perceptron with the back-propagation algorithm (MLP-BP), the dynamic neural network (DAN2), and two hybrid ANNs. The hybrid models used the error produced by the Fourier series forecasting as input to the MLP-BP and DAN2, called ANN-H and DAN2-H, respectively. The tested inputs for the neural network were selected literature and correlation analysis. The results from the hybrid models were promising, DAN2 performing better than the tested MLP-BP models. DAN2-H, identified as the best model, produced a mean absolute error (MAE) of 3:3 L∕s and 2:8 L∕s for training and test set, respectively, for the prediction of the next hour, which represented about 12% of the average consumption. The best forecasting model for the next 24 hours was again DAN2-H, which outperformed other compared models, and produced a MAE of 3:1 L∕s and 3:0 L∕s for training and test set respectively, which represented about 12% of average consumption.

show abstract

Short‐term water demand forecast modeling techniques—CONVENTIONAL METHODS VERSUS AI

Cited by 134 publications

References 12 publications

City Water Demand Forecasting Based on Improved BP Neural Network

City Water Demand Forecasting Based on Improved BP Neural Network

Water demand forecasting using extreme learning machines

Hybrid Water Demand Forecasting Model Associating Artificial Neural Network with Fourier Series

Contact Info

Product

Resources

About