Water Consumption Forecasting Research Articles

A Real-Time Data Analysis Platform for Short-Term Water Consumption Forecasting with Machine Learning

This article presents a real-time data analysis platform to forecast water consumption with Machine-Learning (ML) techniques. The strategy fully relies on a web-oriented architecture to ensure better management and optimized monitoring of water consumption. This monitoring is carried out through a communicating system for collecting data in the form of unevenly spaced time series. The platform is completed by learning capabilities to analyze and forecast water consumption. The analysis consists of checking the data integrity and inconsistency, in looking for missing data, and in detecting abnormal consumption. Forecasting is based on the Long Short-Term Memory (LSTM) and the Back-Propagation Neural Network (BPNN). After evaluation, results show that the ML approaches can predict water consumption without having prior knowledge about the data and the users. The LSTM approach, by being able to grab the long-term dependencies between time steps of water consumption, allows the prediction of the amount of consumed water in the next hour with an error of some liters and the instants of the 5 next consumed liters in some milliseconds.

Short-term forecasting of monthly water consumption in hyper-arid climate using recurrent neural networks

Freshwater supply is a major challenge in regions with limited water resources and extremely arid climatic conditions. The objective of this study is to model the monthly water demand in Kuwait using the nonlinear autoregressive with exogenous input (NARX) neural network approach. The country lacks conventional surface water resources and is characterized by extremely arid climate. In addition, it has one of the fastest growing populations. In this study, linear detrending is performed on the water consumption time series for the period from January 1993 to December 2018 to eliminate the influence of population growth before application to the NARX model. Monthly temperature data are selected as exogenous input to the NARX model, because they are strongly associated with the water consumption data. Correlation analyses are performed to determine the input and feedback delays of the NARX model. The results demonstrate that the recurrent NARX model is efficient and robust for forecasting the short-term water demand, with a Nash-Sutcliffe (NS) coefficient of 0.837 in the validation period. Seasonal model assessment shows that the model performs best during the critical summer season. The NARX-based recurrent model is established as a powerful and promising tool for predicting urban water demand. Thus, it can efficiently aid the development of resilient water supply plans.

Forecast of Water Consumption in the Russian Part of the Don Basin

Forecast of Water Consumption in the Russian Part of the Don Basin

Forecast of annual water consumption in 31 regions of China considering GDP and population

Abstract At present, water resources shortage has become one of the important factors restricting China's economic development, and water consumption prediction is the core task of water resources management. In this paper, a grey multivariate convolution model with adjacent accumulation (AGMC(1,N)) was proposed to predict the annual water consumption of 31 regions (provinces, municipalities and autonomous regions) in China under different growth rates of regional GDP and population. The results show that AGMC(1,N) model has a higher prediction accuracy. In addition, water consumption in more than 50% of the regions shows a downward trend due to the growth of regional GDP. Because of the influence of population, water consumption is also on the decline in more than 50% of areas. The predictive results can provide a basis for water resources management in China.

Forecasting water consumption on transboundary water resources for water resource management using the feed-forward neural network: a case study of the Nile River in Egypt and Kenya

Water resources are an essential component of a country’s natural resource potential. Pressure on these resources is set to increase due to increased water demand, climate change and rainfall variability. This could lead to conflicts between sectoral users, within or between countries, especially among transboundary countries. Interest in transboundary water resources is a priority, especially where issues such as uncertainty regarding the status of transboundary waterbodies and reductions in water volume persist. In this study, we used the feed-forward neural network to forecast water demand along the Nile River in two countries, Egypt and Kenya. Two scenarios were modelled. Input data for the first scenario included preceding records of precipitation, gross domestic product, population and water use in the agricultural sector. The second scenario observed the effects of the growing economy on water resources by doubling the gross domestic product and keeping all other inputs constant. For Kenya, the results projected a steady increase in water demand throughout the next 20 years for both scenarios. However, for Egypt, the observed trend in both scenarios was a decline in water demand, followed by a steady increase. The results underscore the importance of forecasting for easier future planning and management, and to help governing bodies along transboundary water resources develop timely strategies in the future to alleviate future water shortages and poor management of water resources.

Annual Water Consumption Forecast of Hefei Based on ARIMA Model

The ARIMA entity model was used in Hefei's current water demand coding sequence from 1990 to 2018. According to the ADF (Unit Root Test), it is clear that the number of differences d in the entity model is 2, and the main parameters in the entity model p, q are basic identification based on time series analysis related graphs, and based on the Akaike Information Content Rule (AIC) and other methods It is clear that the optimal entity model is ARIMA (1,2,1). ARIMA (1,2,1) is used to predict and analyze Hefei's water demand in the next two years. The results show that the reason for the deviation between the estimated value and the specific value is relatively small, indicating that the actual effect of the actual model predictive analysis is excellent.

Химический состав моющего раствора воды после промывки колесных пар железнодорожного транспорта

The article discusses the impact of economic and industrial water consumption on the state of the hydrosphere and biosphere of the Earth, and also presents the water consumption in Russia, the share of the country's water resources consumed per year and the forecast of water consumption at the end of 2020. The classification of modern methods of wastewater treatment, including in railway depots, is considered. The water consumption and the proportion of circulating water at railway enterprises are analyzed in detail, as well as the most used methods of purification of the used detergent solution (DS) in the enterprise are presented. The description of the work presents the key characteristics of the DS after washing the wheelsets of railway transport, such as pH, total hardness, density and permanganate oxidizability. The data obtained were compared with the requirements (2.1.4.1074-01) and concluded that the water was unsuitable for further operation due to a significant excess of the norm for permanganate oxidizability. The effect of long-term sedimentation of the studied DS was investigated, after which DS was successfully separated into an aqueous phase, an organic phase, a black amorphous organic precipitate, and a yellow amorphous precipitate. The influence of a direct electric current, conducted through the solution at room temperature on carbon electrodes, was studied for a time of 30 minutes, one and three hours. The influence of changes in the pH of the DS medium with subsequent settling was studied. The results of chemical purification of the water under study with such coagulants as ammonium polymolybdate and bismuth(III) salts, the latter of which made it possible to precipitate phosphate ions from solution, are presented. A qualitative reaction with the use of ammonium thiocyanate proved the content of iron(III) ions in the test solution.

Monitoring and forecasting water consumption and detecting leakage using an IoT system

Abstract Water is an important resource for life and its existence and, unfortunately, large quantities of water are being wasted on a daily basis. Monitoring the consumption of water can control water usage, and smart technologies can play a useful role. In this paper, a smart system based on Internet of Things (IoT) has been proposed to monitor the water consumption in an urban housing complex. An ultrasonic sensor, together with Arduino, continuously monitors the water level of water tanks on rooftops and sends these data to a server through a Wi-Fi module. Using the data collected from the IoT system, the daily and weekly average water requirement of households can be calculated. Support vector machines (SVM) are used to forecast water consumption. The observed readings are divided into training and testing datasets. Water consumption is predicted for each day for a user. Error is recorded as the difference between the actual consumption and the predicted value, and it decreases as the number of days increase. An algorithm to monitor leakage of water in the tanks has also been proposed. A web interface allows the user to visualize the water usage, monitor their consumption, and detect any leakage and leakage rate in the system.

Nonlinear Dynamic Modeling of Urban Water Consumption Using Chaotic Approach (Case Study: City of Kelowna)

This study investigated urban water consumption complexity using chaos theory to improve forecasting performance to help optimize system management, reduce costs and improve reliability. The objectives of this study were to (1) investigate urban water distribution consumption complexity and its role in forecasting technique performance, (2) evaluate forecasting models by periodicity and lead time, and (3) propose a suitable forecasting technique based on operator applications and performance through various time scales. An urban consumption dataset obtained from the City of Kelowna (British Columbia, Canada) was used as a test case to forecast future consumption values using varying lead times under different temporal scales to identify models which may improve forecasting performance. Chaos theory techniques were employed to inform model optimization. This study attempted to address the paucity of studies on chaos theory applications in water consumption forecasting. This was accomplished by applying non-linear approximation, dynamic investigation, and phase space reconstruction for input variables, to improve the accuracy in various periodicity and lead time. To reconstruct the phase space, lag time was calculated using average mutual information for daily resolution as 17 days to reconstruct the phase space. The optimum embedding dimension and correlation exponent for the phase space were 18 and 3.5, respectively. Comparing the results, the non-linear local approximation model provided the best performance. The forecasting horizon for the models was 122 days. Moreover, phase space reconstruction improved the accuracy of the models for the different lead times. The findings of this study may improve forecasting performance and provide evidence to support further investigation of the chaotic behaviour of water consumption values over different time scales.

Household Forecasts for the Planning of Long‐Term Domestic Water Demand: Application to London and the Thames Valley

AbstractMethods for forecasting households in London and the Thames Valley were developed for input to forecasts of domestic water consumption. Households were forecast by ethnicity, size and property type. South Asian‐headed households consumed more water (per capita) than average. Forecast populations for 60 Local Authorities were extracted from a UK‐wide forecast and aggregated to six Water Resource Zones (WRZs). Household populations by age, sex and ethnicity were multiplied by trended headship rates to forecast households. Households were classified by size and property type using census microdata. Water demand was generated using modelled consumption rates, based on policy interventions. Between 2011 and 2101, the region will experience 85% growth in populations and 113% in households. The household growth will vary across WRZs between 54% and 126%. Water demand in London and the Thames Valley is forecast to grow by 90%, 69% and 46% under status quo, moderate and extreme conservation scenarios. The future growth in water demand under all scenarios poses a huge challenge for the region, already under water stress.

Forecasting Residential Water Consumption in California: Rethinking Model Selection

AbstractUrban water managers use forecasts of water consumption to determine management decisions and investment choices. Public reports show that water utilities rely on forecast models that are not selected based on their out‐of‐sample prediction performance; further, these reports frequently only present a single forecast instead of a range of forecasts. In our review of the academic literature on forecasting long‐term water consumption, only a few analyses consider out‐of‐sample prediction performance measures to assess prediction ability. In none of these analyses did out‐of‐sample prediction performance drive model selection. Ensemble‐type long‐term forecasts based on multiple models were also lacking. Using annual data on single‐family residential water consumption in Southern California, we show that predictive ability varies drastically depending on how the forecast model is selected. As an illustration of how forecast performance is affected when the criteria for model selection does support forecasting objectives, we compare statistical models with the best in‐sample and out‐of‐sample prediction performance. We find that the models with the best in‐sample performance over‐estimate consumption five years out by 10%‐25% compared to actual consumption. In contrast, the top 1% of models selected based on out‐of‐sample prediction performance came within 1% of actual consumption. Finally, we compare the performance of our ensemble‐type forecasts to those reported in public documents derived from models selected based on non‐out‐of‐sample prediction performance criteria. Our results highlight the benefits of (i) using an out‐of‐sample evaluation criterion to guide model selection and (ii) reporting ensemble forecasts in lieu of a single forecast.

FORECASTING OF THE EXTREME WINTER LOW FLOW FOR THE NORILKA RIVER

The object of the study is the Norilka River, located in the North of the Krasnoyarsk territory. Only 45% of the norm of precipitation fell in the basin of the Norilka River for the period from October 2012 to May 2013, that resulting in an extremely low spring flood formation. The feeding of the large lakes that form the river flow was also limited, as dry weather set in during the summer. This caused great concern regarding the water availability of water intakes of mining and processing plant in the city of Norilsk for the winter of 2014. The situation required the solution of a complex of hydrological tasks, the main of which is the development of a forecast of minimum water consumption for the winter of 2014. The forecast was developed using relationship between area pre-winter moistening with intensity of the winter runoff depletion. Since the capacity of the ice cover can significantly affect to decrease of the river flow, the hydrological forecast takes into account the long-term air temperatures forecast for 2013-2014 winter period. It was obtained the forecast that the minimum monthly discharge for April would be at about 22 m3/s, meanwhile daily discharge 20 m3/s. The received results were a basis for carrying out the measures directed on maintenance of steady water supply with need discharge in 7 m3/s. The low ground dam below water intakes was arranged at backwater on a site of water intakes for August-September 2013. The actual flow discharge for April 2014 was about 14 m3/s. Therefore, the construction of the dam was justified and interruptions of water supply of the plant did not happen. The methodological approaches applied to the solution of this problem can be useful in case of similar situations in the Northern regions of Russia.

Water-resource substantiation of strategic planning in the regions of the Ob-Irtysh basin

The paper substantiates the need to conduct water assessment for the strategic planning documents of the regions, including the elaboration of strategies and the forecasts of long-term socio-economic development of the Russian Federation. In this regard, we present the theoretical and methodological approach and the algorithm of such assessments. The approach is based on the landscape-basin principle of territory organization. On the example of the Ob-Irtysh basin regions, the assessing has revealed water availability in the territories, anthropogenic load, water intensity, water consumption forecast, and prospects for water resources use. They indicate local water shortage in some landscape provinces of Omsk Oblast with a total population of more than 130 thousand people. Within the boundaries of river basins, we have estimated the anthropogenic load of low and medium intensity and calculated water intensity of territories (municipal districts), including for different types of economic activity and yearly dynamics. These results have been also a basis for forecasting the prospective use of water resources for drinking, industrial, irrigation and agricultural purposes. Using the forecasts, we have developed scenarios of the water supply of the regions, considering water content (minimum, maximum and average) of the period.

Forecast of urban water consumption under the impact of climate change

The proper planning of future urban water supply is essential to sustainable development. This paper answers two questions: What quantity of water will be needed in the long term? To what extent will water consumption be affected by climate change? We forecast water consumption using Bayesian statistics methods. A clustering analysis of observed daily water consumption and climate variables splits observations into base water use and seasonal water use, on the basis of the correlation between water consumption and air temperature. We show that the base water use is independent of climate change, but is subject to weekend effects. The seasonal water use depends on daily air temperature and total precipitation. Our forecast allows for uncertainties in climate variables and model parameters. The results from Bayesian linear regression give a probability distribution of daily water use. We obtained climate projections from multiple general circulation models and downscaled them for Greater Montreal. Bias corrections were made to the downscaled daily minimum temperature, maximum temperature and total precipitation. Using these corrected data as input to the Bayesian linear regression model, we forecast water consumption for the next three decades. The forecast results show a trend of increasing seasonal water use over time.

Urban Water Demand Forecasting: A Comparative Evaluation of Conventional and Soft Computing Techniques

Previous studies have shown that soft computing models are excellent predictive models for demand management problems. However, their applications in solving water demand forecasting problems have been scantily reported. In this study, feedforward artificial neural networks (ANNs) and a support vector machine (SVM) were used to forecast water consumption. Two ANN models were trained using different algorithms: differential evolution (DE) and conjugate gradient (CG). The performance of these soft computing models was investigated with real-world data sets from the City of Ekurhuleni, South Africa, and compared with conventionally used exponential smoothing (ES) and multiple linear regression (MLR). The results obtained showed that the ANN model that was trained with DE performed better than the CG-trained ANN and other predictive models (SVM, ES and MLR). This observation further demonstrates the robustness of evolutionary computation techniques amongst soft computing techniques.

Extended linear and non-linear auto-regressive models for forecasting the urban water consumption of a fast-growing city in an arid region

Accurate water consumption forecasting models are required for fast-growing cities in arid regions. In the present study, two forecasting models are proposed for urban-water consumption using extended Auto-Regressive Integrated Moving Average (ARIMA) and Nonlinear Auto-Regressive Exogenous (NARX) methods. Various extension of these models by adding new forecaster factors were tested to find superior linear and nonlinear models. The ARIMA and NARX model accuracy with and without additional forecaster factors (minimum, maximum and mean temperature, precipitation, mean relative humidity, sunshine hours, mean dew point temperature, mean wind speed, and population) were compared using accuracy indices. The ARIMA model which includes sunny hour in addition to the base model predictors was selected as the superior linear model and also the model NARX which includes sunny hours and population in addition to the base model’s predictors was selected as the superior nonlinear model. This infers that sunny hour has linear performance and population predictor has non-linear performance in forecasting water consumption. This shows adding sunny hours and population as forecaster factors can robust forecasting performance considerably. By extending the models with these additional forecasting factors, the precision of daily water consumption forecasts can be improved for providing a better urban water supply.

Bayesian regularized NAR neural network based short-term prediction method of water consumption

With the continuous construction of urban water supply infrastructure, it is extremely urgent to change the management mode of water supply from traditional manual experience to modern and efficient means. The water consumption forecast is the premise of water supply scheduling, and its accuracy also directly affects the effectiveness of water supply scheduling. This paper analyzes the regularity of water consumption time series, establishes a short-term water consumption prediction model based on Bayesian regularized NAR neural network, and compares and evaluates the prediction effect of the model. The verification results show that the Bayesian based NAR neural network prediction model has higher adaptability to the water consumption prediction than the standard BP neural network and the Bayesian regularized BP neural network. The prediction accuracy can more accurately reflect the short-term variation of water consumption.

Forecasting water consumption in towns of different sizes

The aim of the work was to compare water consumption forecasting in two towns of different sizes. The objects of research were the town of Toruń and the town of Żnin in central Poland. Two models were built for each. The models were constructed using the multiple regression method. In constructing the models, explanatory variables determined by Principal Component Analysis (PCA) were used. The set of explanatory variables identified to construct each individual model differed. The models for Toruń obtained better forecast quality assessment criteria values. This was mainly due to the water supply system in the small town (Żnin) being less resilient to sudden, short-term changes in consumers’ water use. At the same time, the importance of the location of the meteorological stations from which data was taken to build the model was emphasised.

Forecasting of Water Consumptions Expenditure Using Holt-Winter’s and ARIMA

This study is carried out to forecast water consumption expenditure of Malaysian university specifically at University Tun Hussein Onn Malaysia (UTHM). The proposed Holt-Winter’s and Auto-Regressive Integrated Moving Average (ARIMA) models were applied to forecast the water consumption expenditure in Ringgit Malaysia from year 2006 until year 2014. The two models were compared and performance measurement of the Mean Absolute Percentage Error (MAPE) and Mean Absolute Deviation (MAD) were used. It is found that ARIMA model showed better results regarding the accuracy of forecast with lower values of MAPE and MAD. Analysis showed that ARIMA (2,1,4) model provided a reasonable forecasting tool for university campus water usage.

The development of an integrated model for the assessment of water and GHG footprints for the power generation sector

To ensure the use of water today does not damage the prospects for its use by future generations, there is need to understand long-term water demand and supply through energy production, conversion, and use. This study aims to develop an integrated framework to assess the long-term impacts of climate change scenarios on water requirements and greenhouse gas (GHG) emissions. The framework includes the integration of the Water Evaluation And Planning model (WEAP) and the Long-range Energy Alternative Planning Systems model (LEAP). As many countries are planning to move towards a cleaner electricity grid to mitigate climate change, this work attempts to present the impact of various scenarios on water demand, GHG emissions, and cost effectiveness. This is done by conducting a case study of the western Canadian province of Alberta where more than 85% of electricity is generated by fossil fuels. This paper provides a comprehensive overview of nine integrated LEAP-WEAP climate change scenarios for the years 2015–2050 by forecasting water consumption and greenhouse gas emissions from the power sector. The economic aspects of the developed scenarios are discussed in the form of a cost curve that shows the GHG saving potential, water use, and GHG mitigation costs for each scenario. For the Business-As-Usual (BAU) scenario (coal power phase out by 2030), GHG emissions and water demand will fall by 44% and 34%, respectively, in 2030. The integrated results show that the scenarios will mitigate carbon emissions but will result in higher water consumption, which will directly affect water resources in the region. Because of the high investment cost to install the considered renewable power plants in the climate change scenarios, the cost of mitigating carbon emissions in the power sector is high. Early coal-to-gas power plant conversion is the only scenario that is expected to save water (67 million m3) and reduce emissions (40 million tonnes of CO2 eq.) and be cost effective ($68/tonne of CO2 eq.). These LEAP-WEAP model results can help create awareness among policy makers to understand the water-energy demand and supply relationship in a quantifiable way.