Smart meters data for modeling and forecasting water demand at the user-level

Pesantez, Jorge E.; Berglund, Emily Zechman; Kaza, Nikhil

doi:10.1016/j.envsoft.2020.104633

Cited by 67 publications

(42 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“… Socio-technical Determinant Explanation/Reference Technical Previous water demand (lagged) Water demand depends on its past values ( Alhumoud, 2008 ; Bougadis et al, 2005 ; Hutton and Kapelan, 2015 ; Jain et al, 2001 ; Jain and Ormsbee, 2002 ; Jentgen et al, 2007 ; Pesantez et al, 2020 ; Wu and Zhou, 2010 ; Zhou et al, 2000 ); e.g., weekly water demand is highly correlated with water demand in the previous week ( Jain et al, 2001 ) Environmental Climatic Maximum air temperature Increases in water demand when maximum air temperature increases, especially during dry periods ( Bougadis et al, 2005 ; Goodchild, 2003 ; House-Peters and Chang, 2011 ; Jain et al, 2001 ; Jain and Ormsbee, 2002 ; Jentgen et al, 2007 ; Pesantez et al, 2020 ; Zhou et al, 2000 ) Rainfall amount Decreases in weekly water demand when there is increasing rainfall volume ( Bougadis et al, 2005 ; Goodchild, 2003 ; House-Peters and Chang, 2011 ; Jain et al, 2001 ; Jain and Ormsbee, 2002 ; Jentgen et al, 2007 ) Rainfall occurrence Decrease in water use when rainfall occurs (defined as rainfall amount > given threshold value) ( Jain and Ormsbee, 2002 ; Maidment and Parzen, 1984 ); i.e., rainfall occurrence is set to 1, with rainfall a...…”

Section: Methodsmentioning

confidence: 99%

“…For instance, an increase in the maximum air temperature can lead to increases in water demand—especially during dry periods—largely due to increases in outdoor watering ( Bougadis et al, 2005 ). Additionally, water demand varies across geographic areas ( House-Peters and Chang, 2011 ) (e.g., residential areas versus commercial areas) and typically exhibits different patterns throughout weekdays ( Cutore et al, 2008 ; Pesantez et al, 2020 ). We refer to these temporal and spatial trends as spatial and temporal effects in water demand.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Impacts of COVID-19 social distancing policies on water demand: A population dynamics perspective

Bakchan

Roy

Faust

2022

Journal of Environmental Management

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Impacts of COVID-19 social distancing policies on water demand: A population dynamics perspective

Bakchan

Roy

Faust

2022

Journal of Environmental Management

View full text Add to dashboard Cite

“…SVR shows excellent capability of generalization with high accuracy. The basic idea of SVR is to map the nonlinear input data into a higher-dimensional feature space and form a linear function as follows [44][45][46][47][48]:…”

Section: Support Vector Regressionmentioning

confidence: 99%

An Innovative Hourly Water Demand Forecasting Preprocessing Framework with Local Outlier Correction and Adaptive Decomposition Techniques

Gao

Zhong

et al. 2021

Water

View full text Add to dashboard Cite

Accurate forecasting of hourly water demand is essential for effective and sustainable operation, and the cost-effective management of water distribution networks. Unlike monthly or yearly water demand, hourly water demand has more fluctuations and is easily affected by short-term abnormal events. An effective preprocessing method is needed to capture the hourly water demand patterns and eliminate the interference of abnormal data. In this study, an innovative preprocessing framework, including a novel local outlier detection and correction method Isolation Forest (IF), an adaptive signal decomposition technique Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), and basic forecasting models have been developed. In order to compare a promising deep learning method Gated Recurrent Unit (GRU) as a basic forecasting model with the conventional forecasting models, Support Vector Regression (SVR) and Artificial Neural Network (ANN) have been used. The results show that the proposed hybrid method can utilize the complementary advantages of the preprocessing methods to improve the accuracy of the forecasting models. The root-mean-square error of the SVR, ANN, and GRU models has been reduced by 57.5%, 27.8%, and 30.0%, respectively. Further, the GRU-based models developed in this study are superior to the other models, and the IF-CEEMDAN-GRU model has the highest accuracy. Hence, it is promising that this preprocessing framework can improve the performance of the water demand forecasting models.

show abstract

“…RF algorithm uses the Classification and Regression Trees (CART) in the creation of the decision tree. GINI index are used to evaluate performance of the decision trees that are created by CART and to create new branches [38]. Differently, RF doesn't use all features while creating new trees but choose the features randomly to create them.…”

Section: Random Forestmentioning

confidence: 99%

Machine Learning Algorithms with Intermittent Demand Forecasting: An Application in Retail Apparel with Plenty of Predictors

Güven

Uygun

Şimşir

2021

Tekstil Ve Konfeksiyon

View full text Add to dashboard Cite

Demand forecasting is a key factor for apparel retail stores to sustain their business, especially where there are variety of products and intermittent demand. In this study, two of the most popular machine learning methods, random forest (RF) and k-nearest neighbour (KNN), have been used to forecast retail apparel's intermittent demand. Numerous variables that may have an effect on the sales, have been taken into account one of which is defined as "special day" that might trigger intermittency in the demand. During the forecast application, four different datasets were used to provide reliability. 28 different variables were used to increase accuracy of the forecasting and experience of the behaviours of the algorithms. Root mean square error (RMSE) was used to evaluate performance of the methods and as a result of this study, RF showed better performance in all four datasets comparing to KNN.

show abstract

Smart meters data for modeling and forecasting water demand at the user-level

Cited by 67 publications

References 64 publications

Impacts of COVID-19 social distancing policies on water demand: A population dynamics perspective

Impacts of COVID-19 social distancing policies on water demand: A population dynamics perspective

An Innovative Hourly Water Demand Forecasting Preprocessing Framework with Local Outlier Correction and Adaptive Decomposition Techniques

Machine Learning Algorithms with Intermittent Demand Forecasting: An Application in Retail Apparel with Plenty of Predictors

Contact Info

Product

Resources

About