Short-term demand forecast using a bank of neural network models trained using genetic algorithms for the optimal management of drinking water networks

Rangel, Héctor Rodríguez; Puig, Vicenç; Farías, Rodrigo López; Flores, Juan J.

doi:10.2166/hydro.2016.199

Cited by 21 publications

(15 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Rodriguez Rangel et al [8] used the concept of daily patterns (modes) predicted with the non-parametric Nearest Neighbor Mode Estimation (NNME) proposed in Lopez Farias et al [6]. NNME is used as a regression method to forecast the modes that feeds the input of an ensemble of 24 independent artificial neural network (ANN) models trained with Genetic Algorithms; each of the ANN predicts a specific hour of the day.…”

Section: Related Workmentioning

confidence: 99%

“…A similar approach proposed by Candelieri [9], suggests the use of several pools (each pool associated with a type of the day) with 24 Support Vector Machines Models, each one to predict a specific hour of the day. In contrast to Rodriguez Rangel et al [8], Candelieri's method only classifies the current day to select the pool. Donkor et al [10] report the use of different methodologies to improve the water demand prediction in the short term (from several hours to several days ahead) and the long term (one year or more ahead); nevertheless, it does not propose the use of regimes.…”

Section: Related Workmentioning

confidence: 99%

“…where F NN receives the recent vector C I T I=T−(m+1) as an argument and it is set to D T using Equation (8). ∆H represents time index increments generating the next class labels sequence of size H from v j + 1 to v j + H of each D v j .…”

Section: Nearest Neighbors Mode Estimatormentioning

confidence: 99%

See 2 more Smart Citations

Multi-Model Prediction for Demand Forecast in Water Distribution Networks

et al. 2018

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Model Prediction for Demand Forecast in Water Distribution Networks

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…Esto es, imita una versión simplista del proceso de evolución biológica, que consiste en crear una población de individuos, donde cada individuo representa una solución prospectiva del problema que se está resolviendo. AG modifica esta población utilizando operadores genéticos: selección, mutación y recombinación [17].…”

Section: Construcción Del Modelo De Series De Tiempounclassified

Pronóstico a corto plazo de velocidad del viento a partir de datos incompletos

Rangel¹,

Carrillo²,

Flores³

et al. 2017

RCS

Self Cite

View full text Add to dashboard Cite

Resumen. En este artículo se presenta un estudio realizado a la predicción a corto plazo de la velocidad del viento en series de tiempo incompletas. Se ha propuesto realizar este estudio dado el incremento en el interés hacia la transición global de la producción de energías limpias. Siendo el pronóstico de dicha variable de suma importancia para las etapas de planeación, administración y producción. El proceso de pronóstico implica el uso de observaciones pasadas de la variable a pronosticar (velocidad del viento). Para medir la velocidad del viento, las estaciones meteorológicas utilizan dispositivos llamados anemómetros, pero debido a un mal mantenimiento, errores de conexión o desgaste natural, pueden presentar datos falsos o faltantes. En este trabajo, se explora la reconstruión la serie de tiempo mediante Redes Neuronales Artificiales, para posteriormente realizar el pronóstico a corto plazo de la serie de tiempo de la velocidad del viento utilizando el método de k Vecinos más Cercanos. Para probar la metodología propuesta, se utilizaron datos recolectados de diferentes locaciones del estado de Michoacán.Palabras clave: pronóstico de la velocidad del viento, recostrucción de series de tiempo, RNA, kNN.Abstract. This paper presents a wind speed short-term forecasting from incomplete time series. This study has been proposed given the interest increasing in a global transition of clean energy production. Being

show abstract

“…Pacchin et al () forecasted hourly demands based on simple ratios of recent 24 h total demands and specific time of day demands. Apart from the statistical approaches of MLR and time series analysis, other approaches such as Artificial Neural Networks (ANNs; Bougadis et al, ; Jacobsen & Kamojjala, ; Jain & Ormsbee, ), ensemble ANNs (i.e., generating ANNs for individual hours within a day; Rangel et al, ; Romano & Kapelan, ), wavelet‐bootstrap‐neural networks (Tiwari & Adamowski, ), Relevance Vector Regression with wavelet transforms (Bai et al, ), Support Vector Regression (SVR; Bai et al, ), and SVR with a Fourier series representation of the predicted deviations (Brentan et al, ) have also been used for demand representation and/or forecasting. While these approaches capture nonlinear aspects of demand dynamics, these models have generally been applied to daily, or longer, time intervals for total demands without capturing forecasted uncertainties.…”

Section: Introductionmentioning

confidence: 99%

Forecasting Hourly Water Demands With Seasonal Autoregressive Models for Real‐Time Application

Jin-duan

Boccelli

2018

Water Resources Research

View full text Add to dashboard Cite

Consumer water demands are not typically measured at temporal or spatial scales adequate to support real‐time decision making, and recent approaches for estimating unobserved demands using observed hydraulic measurements are generally not capable of forecasting demands and uncertainty information. While time series modeling has shown promise for representing total system demands, these models have generally not been evaluated at spatial scales appropriate for representative real‐time modeling. This study investigates the use of a double‐seasonal time series model to capture daily and weekly autocorrelations to both total system demands and regional aggregated demands at a scale that would capture demand variability across a distribution system. Emphasis was placed on the ability to forecast demands and quantify uncertainties with results compared to traditional time series pattern‐based demand models as well as nonseasonal and single‐seasonal time series models. Additional research included the implementation of an adaptive‐parameter estimation scheme to update the time series model when unobserved changes occurred in the system. For two case studies, results showed that (1) for the smaller‐scale aggregated water demands, the log‐transformed time series model resulted in improved forecasts, (2) the double‐seasonal model outperformed other models in terms of forecasting errors, and (3) the adaptive adjustment of parameters during forecasting improved the accuracy of the generated prediction intervals. These results illustrate the capabilities of time series modeling to forecast both water demands and uncertainty estimates at spatial scales commensurate for real‐time modeling applications and provide a foundation for developing a real‐time integrated demand‐hydraulic model.

show abstract

Short-term demand forecast using a bank of neural network models trained using genetic algorithms for the optimal management of drinking water networks

Cited by 21 publications

References 30 publications

Multi-Model Prediction for Demand Forecast in Water Distribution Networks

Multi-Model Prediction for Demand Forecast in Water Distribution Networks

Pronóstico a corto plazo de velocidad del viento a partir de datos incompletos

Forecasting Hourly Water Demands With Seasonal Autoregressive Models for Real‐Time Application

Contact Info

Product

Resources

About