scholarly journals Committee Machines for Hourly Water Demand Forecasting in Water Supply Systems

2019 ◽  
Vol 2019 ◽  
pp. 1-11 ◽  
Author(s):  
Julia K. Ambrosio ◽  
Bruno M. Brentan ◽  
Manuel Herrera ◽  
Edevar Luvizotto ◽  
Lubienska Ribeiro ◽  
...  
Keyword(s):  
Water Supply ◽  
Water Demand ◽  
Prediction Models ◽  
Fuzzy Inference ◽  
Demand Forecasting ◽  
Accurate Estimation ◽  
Support Vector ◽  
Multilayer Perceptrons ◽  
Group Method ◽  
Water Supply Systems

Prediction models have become essential for the improvement of decision-making processes in public management and, particularly, for water supply utilities. Accurate estimation often needs to solve multimeasurement, mixed-mode, and space-time problems, typical of many engineering applications. As a result, accurate estimation of real world variables is still one of the major problems in mathematical approximation. Several individual techniques have shown very good estimation abilities. However, none of them are free from drawbacks. This paper faces the challenge of creating accurate water demand predictive models at urban scale by using so-called committee machines, which are ensemble frameworks of single machine learning models. The proposal is able to combine models of varied nature. Specifically, this paper analyzes combinations of such techniques as multilayer perceptrons, support vector machines, extreme learning machines, random forests, adaptive neural fuzzy inference systems, and the group method for data handling. Analyses are checked on two water demand datasets from Franca (Brazil). As an ensemble tool, the combined response of a committee machine outperforms any single constituent model.

scholarly journals Sustainability characteristics of drinking water supply

2020 ◽  
Author(s):  
Jolijn van Engelenburg ◽  
Erik van Slobbe ◽  
Adriaan J. Teuling ◽  
Remko Uijlenhoet ◽  
Petra Hellegers
Keyword(s):  
Drinking Water ◽  
Water Supply ◽  
Water Demand ◽  
Supply System ◽  
Water Supply System ◽  
Drinking Water Supply ◽  
Extreme Weather Events ◽  
Water Supply Systems ◽  
Global Issues ◽  
Drinking Water Supply System

Abstract. Developments such as climate change and growing demand for drinking water threaten the sustainability of drinking water supply worldwide. To deal with this threat, adaptation of drinking water supply systems is imperative, not only on a global and national scale, but particularly on a local scale. This investigation sought to establish characteristics that describe the sustainability of local drinking water supply. We use an integrated systems approach, describing the local drinking water supply system in terms of hydrological, technical and socio-economic characteristics that determine the sustainability of a local drinking water supply system. Three cases on drinking water supply in the Netherlands are analysed. One case relates to a short-term development, that is the 2018 summer drought, and two concern long-term phenomena, that is, changes in water quality and growth in drinking water demand. The approach taken recognises that next to extreme weather events, socio-economic developments will be among the main drivers of changes in drinking water supply. Effects of pressures associated with, for example, population growth, industrial developments and land use changes, could result in limited water resource availability, deteriorated groundwater quality and growing water demand. To gain a perspective on the case study findings broader than the Dutch context, the sustainability issues identified were paired with global issues concerning sustainable drinking water supply. This resulted in a proposed set of generally applicable sustainability characteristics, each divided into five criteria describing the hydrological, technical and socio-economic sustainability of a local drinking water supply system. Elaboration of these sustainability characteristics and criteria into a sustainability assessment can provide information on the challenges and trade-offs inherent in the sustainable development and management of a local drinking water supply system.

scholarly journals Diversification of water supply

2018 ◽  
Vol 59 ◽  
pp. 00006
Author(s):  
Janusz Rak ◽  
Krzysztof Boryczko
Keyword(s):  
Water Supply ◽  
Water Demand ◽  
Water Supply Systems ◽  
Water Production ◽  
Total Water ◽  
Parameter Evaluation ◽  
Technical Structure ◽  
The Subject ◽  
Water Tanks ◽  
Supply Systems

The subject of the publication is the presentation of a methodology for determining the degree of diversification of water resources in collective water supply systems (= CWSS). Knowing the number of subsystems for water supply and their share of total water production, it is possible to calculate the dimensionless Pielou index. Similarly, the diversification indicators for networked water tanks (number and volume) and pressure pipelines of the second degree pumping station (number and flowability) can be determined. The work presents the calculation of diversification indices for selected CWSS in Poland. The presented methodology gives the possibility of three-parameter evaluation of settlement units with different water demand and different technical structure.

Predicting water demand: a review of the methods employed and future possibilities

2019 ◽  
Vol 19 (8) ◽  
pp. 2179-2198 ◽  
Author(s):  
Gustavo de Souza Groppo ◽  
Marcelo Azevedo Costa ◽  
Marcelo Libânio
Keyword(s):  
Artificial Intelligence ◽  
Water Supply ◽  
Water Demand ◽  
Supply And Demand ◽  
Demand Forecasting ◽  
System Management ◽  
Water Demand Forecasting ◽  
Combination Of Methods ◽  
Applications Of Machine Learning

Abstract The balance between water supply and demand requires efficient water supply system management techniques. This balance is achieved through operational actions, many of which require the application of forecasting concepts and tools. In this article, recent research on urban water demand forecasting employing artificial intelligence is reviewed, aiming to present the ‘state of the art’ on the subject and provide some guidance regarding methods and models to research and professional sanitation companies. The review covers the models developed using standard statistical techniques, such as linear regression or time-series analysis, or techniques based on Soft Computing. This review shows that the studies are, mostly, focused on the management of the operating systems. There is, therefore, room for long-term forecasts. It is worth noting that there is no global model that surpasses all the methods for all cases, it being necessary to study each region separately, evaluating the strengths of each model or the combination of methods. The use of statistical applications of Machine Learning and Artificial Intelligence methodologies has grown considerably in recent years. However, there is still room for improvement with regard to water demand forecasting.

scholarly journals Methodical basis of the needs of water supply in rural areas in normal and special conditions

2018 ◽  
Vol 59 ◽  
pp. 00022
Author(s):  
Mikołaj Sikorski ◽  
Hanna Bauman-Kaszubska
Keyword(s):  
Water Supply ◽  
Rural Areas ◽  
Water Demand ◽  
Animal Husbandry ◽  
Quality Parameters ◽  
Public Utilities ◽  
Water Supply Systems ◽  
Agricultural Water ◽  
Methodical Basis ◽  
Supply Systems

When calculating the balance of water supply, the purpose for which water is intended should be taken into account. Depending on them, the water quality parameters may vary. Rural and agricultural water demand covers the basic types of water demand, including the population's living and economic needs, animal husbandry, the needs of public utilities, the needs related to the operation of vehicles and machinery, workshops, machines and other purposes, including the own needs of the water pipes, fire-fighting etc. The level of demand is also closely related to the factors influencing the level of individual water consumption. Taking into account the deficiencies in formal and legal regulations, the binding regulations concerning the operation of water supply systems in special conditions have been presented so far. Elements of the benchmarking study on unit water demand indicators in normal and special conditions in rural areas have also been taken into account, guided by the principles and numerical indicators for the calculation of water demand for drinking and business purposes.

Nanotechnology application in water resource management

2021 ◽  
pp. 33-62
Author(s):  
Arezoo Boroomandnia ◽  
Omid Bozorg-Haddad ◽  
Jimmy Yu ◽  
Mariam Darestani
Keyword(s):  
Resource Management ◽  
Water Resources ◽  
Water Supply ◽  
Case Studies ◽  
Water Resource ◽  
Water Demand ◽  
Water Resource Management ◽  
Management Strategies ◽  
Water Supply Systems ◽  
Supply Systems

Abstract Fast-growing water demand, population growth, global climate change, and water quality deterioration all drive scientists to apply novel approaches to water resource management. Nanotechnology is one of the state-of-the-art tools in scientists’ hands which they can use to meet human water needs via reuse of water and utilizing unconventional water resources. Additionally, monitoring water supply systems using new nanomaterials provides more efficient water distribution networks. In this chapter, we consider the generic concepts of nanotechnology and its effects on water resources management strategies. A wide range of nanomaterials and nanotechnologies, including nano-adsorbents, nano-photocatalysts, and nano-membranes, are introduced to explain the role of nanotechnology in providing new water resources to meet growing demand. Also, nanomaterial application as a water alternative in industry, reducing water demand in the industrial sector, is presented. Another revolution made by nanomaterials, also discussed in this chapter, is their use in water supply systems for monitoring probable leakage and leakage reduction. Finally, we present case studies that clarify the influence of nanotechnology on water resources and their management strategies. These case studies prove the importance and inevitable application of nanotechnology to satisfy the rising water demand in the modern world, and show the necessity of nanotechnology awareness for today's water experts.

Interactions and feedbacks between water availability and domestic consumption in São Paulo Metropolitan Area

2020 ◽  
Author(s):  
Felipe Souza ◽  
Gabriela Gesualdo ◽  
Murugesu Sivapalan ◽  
Eduardo Mendiondo
Keyword(s):  
Water Supply ◽  
Metropolitan Area ◽  
Water Availability ◽  
Water Demand ◽  
Hydrological Cycle ◽  
Management Strategies ◽  
Water System ◽  
Water Supply Systems ◽  
Domestic Consumption

<p>Water supply in large cities has challenged governments and water authorities because of the complexity involved in meeting water demands. The traditional challenges stem from the seasonality of precipitation and population growth. Although water resources management strategies assume potential scenarios for water demand growth to design water infrastructure, unexpected changes in the hydrological cycle may cause shocks to urban water supply systems and generate unanticipated patterns of consumption, such as occurred during the water crisis experienced by the São Paulo Metropolitan Area (SPMA) from 2014 to 2016. This work explores the coevolution of the coupled human-water system variables associated with the water supply system within the SPMA, from the late twentieth century to the present, to explain how water demand has influenced water availability, and vice-versa, in particular for the Cantareira Reservoir System. The challenges facing the human-water system in the region are of critical importance, given that it supplies water to more than 9 million people, and it supports economic activities that represent 12% of Brazil’s Gross Domestic Product. The analysis reveals that hydrological shifts are responsible for major structural transformations and they also have led to changes in domestic consumption. We conclude that modelling the interactions and feedbacks between water availability and consumption can provide more realistic storylines to implement strategies to address water scarcity than merely considering long-term demand scenarios, as it is normally done. In addition, policies implemented to promote water savings can have different responses at sub-regional scales and this can be explored also in the context of long-term scenarios.</p>

scholarly journals Water Consumption Variability Based on Cumulative Data From Non-simultaneous and Long-term Measurements

2021 ◽  
Author(s):  
Jacek Wawrzosek ◽  
Syzmon Ignaciuk ◽  
Justyna Stańczyk ◽  
Joanna Kajewska-Szkudlarek
Keyword(s):  
Water Supply ◽  
Water Consumption ◽  
Water Demand ◽  
Fuzzy Time Series ◽  
Water Supply Systems ◽  
Short Term ◽  
Continuous Processes ◽  
Short And Long Term ◽  
Demand Patterns

AbstractDevices for water consumption measurement provide data from periodical readings in a non-simultaneous and cumulative manner. This may result in inaccuracies within the process of inference about the short-term habitual patterns of water supply network users. Maintaining systems at the interface between periodic and continuous processes requires the continuous improvement of research methodology. To obtain reliable results regarding the variability of water consumption, the first step should be to estimate it for each observation day by periodic averaging and a possible water balancing approach, but the analysis of the value of estimators obtained in this way usually does not allow for studying autocorrelation. However, other methods indicate the existence of multiplicative parameters characterizing short- and long-term variations in water demand. The purpose of this study is to create a new and deterministic method for tackling the problem associated with a lack of short-term detailed data with fuzzy time series using a multiplicative model for water consumption. Satisfactory results have been obtained, demonstrating that the dispersed data, received in a cumulative manner for random periods of measurement, can be analyzed by the methodology of proposed statistical inference. The observed variability in water consumption may be used in the planning and modernization of water supply systems, development of water demand patterns, hydraulic models, and in the creation of forecasting models of water consumption.

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

Water ◽  
2021 ◽  
Vol 13 (5) ◽  
pp. 582 ◽  
Author(s):  
Shiyuan Hu ◽  
Jinliang Gao ◽  
Dan Zhong ◽  
Liqun Deng ◽  
Chenhao Ou ◽  
...  
Keyword(s):  
Water Demand ◽  
Water Distribution ◽  
Demand Forecasting ◽  
Cost Effective ◽  
Distribution Networks ◽  
Correction Method ◽  
Support Vector ◽  
Forecasting Models ◽  
Water Demand Forecasting ◽  
Local Outlier

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.

Sign in / Sign up

Export Citation Format

Share Document