Water Distribution Management Research Articles

Optimized Deep Learning Framework for Water Distribution Data-Driven Modeling

Deep Learning (DL), unlike conventional Artificial Neural network (ANN), is capable of self-learning data features layer by layer in unsupervised manner and creating a data-driven model with the given dataset. DL has been widely applied to big data analytics, graphics object detection, classification, voice recognition and many other problems. This paper presents an integrated data-driven modelling framework that couples DL with the well-developed evolutionary optimization tool in a scalable and heterogeneous high performance computing paradigm. The integrated framework enables modellers to effectively and efficiently construct a model with a given dataset. It is demonstrated that the framework has wide applicability including but not limited to the simulation, optimization and operation decision of water distribution systems. The paper elaborates the development of the deep learning framework with potential applications of facilitating the data fusion, system simulation and predictive analysis, anomaly detection from the time series data (pressures, flows and consumptions etc.), water usage prediction, construction of a meta-model as a surrogate to the physics-based models (hydraulic and water quality) for water distribution management.

Build up a database to determine the management of drinking water in the Province of Cartago, Costa Rica

In Costa Rica, the majority of people have drinking water in their homes, but because of climate change along with the increase of population and non-existent planning programs, the distribution of this resource could be affected. To ensure sustainability of drinking water, information on demand and supply is required. Unfortunately, the information is outdated and there is no single unified database to which all management related institutions have access. Costa Rica has many public institutions that perform quality control, monitor and provide licenses for water exploitation. Each institution organizes its information according to their own criteria, therefore, making it impossible to compare the data, and difficult to identify the main problems. The authors verified and compared every database available, aiming to consolidate one database to determinate management of water distribution in Cartago. The main results of this research identified distribution of water suppliers throughout the province, the results were: Aqueduct Administration Associations (27.1%), Municipal Aqueducts (60.2%) and National Costa Rica Aqueducts and Sewerage Institute (AyA) Aqueducts (14.1%). One hundred per cent of Municipal and AyA Aqueducts disinfect and provide potable water, but 25% of Aqueduct Administration Rural Associations do not disinfect the water and there is not enough information about the quality of water that they offer.

Nanoseismic monitoring of gravity-induced slope instabilities for the risk management of an aqueduct infrastructure in Central Apennines (Italy)

A monitoring system is operative in the Peschiera Springs slope (Central Apennines, Italy) to mitigate the landslide risk related to the hosted main drainage plant of Rome aqueducts by providing alert warning. Such a strategy allows to avoid out-of-service episodes so reducing extra-costs of water distribution management. The Peschiera Springs slope is involved in a rock mass creep characterized by an average steady strain rate of 1 mm year−1 and responsible for several landforms including sinkholes, subvertical scarps and trenches. Moreover, an average aquifer discharge of 19 m3 s−1 causes an intense limestone dissolution concentrated in correspondence with release bands and discontinuities that dislodge the jointed rock mass. Since 2008, an accelerometric network has been operating within the slope; about 1300 microseismic local events were recorded up to now, distinguished in failures and collapses. A control index, based on frequency of occurrence and cumulative energy of the recorded microseismic events was defined to provide three levels of alert. In 2013, a temporary nanoseismic Seismic Navigation System (SNS) array was installed inside a tunnel of the drainage plant to integrate the pre-existent seismic monitoring system. This array allowed to record 37 microseismic events, which locations are in good agreement with the evolutionary geological model of the ongoing gravitational slope deformation. In 2014, a permanent nanoseismic SNS array was installed in the plant and allowed to record several sequences of underground collapses including more than 500 events. The nanoseismic monitoring system is allowing to: (1) increase the detection level of the monitoring system; (2) locate hypocentres of the events; and (3) detect precursors of the strongest events.

Experimental characterization of two Pumps As Turbines for hydropower generation

In recent years, the use of turbines or Pumps operating As Turbines (PATs) has been proven to be a sustainable alternative for managing Water Distribution Networks (WDNs), by coupling pressure control and leakage reduction with hydropower generation.Pumps running in reverse mode can be an effective alternative to using turbines for energy production in WDNs. Many commercial models are readily available on the market and a number of economic and technical advantages for installation, operation and maintenance can be found. Theoretical and experimental criteria for predicting pump performance in turbine mode and for the optimal installation of a PAT in WDNs can be found in the literature. Nevertheless, the prediction of PAT characteristic curves is still an unresolved issue, because of the lack of information provided by manufacturers and the few laboratory campaigns that focus on the topic.For this purpose, the laboratory results in the present study aim to assess the performance of pumps operating in reverse mode. Two centrifugal pumps were investigated: a centrifugal horizontal single-stage pump and a vertical multi-stage pump. Experiments were compared with theoretical models available in the literature, in order to assess their reliability in predicting PAT performance when data are lacking.

Ecuadorian students’ conceptions and personal experience regarding water management issues / Concepciones y experiencias personales de los estudiantes ecuatorianos sobre la gestión del agua

Household water distribution and wastewater management represent major challenges in developing countries. In designing effective instructional interventions to address this issue, educators should consider people’s current knowledge of water management as a starting point. In our study, we examine Ecuadorian students’ current conceptions and personal experience in the context of water management issues. A sample of 73 adolescents from the Guayas coastal region of Ecuador responded to a paper-pencil questionnaire with open questions. The subsequent qualitative content analysis revealed some interesting results. In particular, the students’ life experiences appear to shape the students’ conceptions regarding the origin of piped-in household water and its ultimate destination, suggesting that experience-based learning has occurred. We found that a confusion of issues may arise. Mixing up the household water system with the wastewater system or household water with bottled water may lead to overgeneralization. Technical terms like groundwater, waterworks and wastewater treatment plant seem to be unfamiliar to most Ecuadorian students. Inferring from our results, we present practical recommendations for educators, both in developed and developing countries, to use in their instruction on water management issues.

A Bayesian Approach to Predicting Water Supply and Rehabilitation of Water Distribution Networks

Water distribution network (WDN) consists of several elements the main ones: pipes and valves. The work developed in this article focuses on a water supply prediction in the short and long term. To this end, reliability data were conjugated in decision making tools on water distribution network rehabilitation in a forecasting context. The pipes are static elements that allow the transport of water to customers, while the valves are dynamic components which perform ensure management of water flow. This paper presents a Bayesian approach that allows management of water distribution network based on the evaluation of the reliability of network components. Modeling based on a Static Bayesian Network (SBN) is implemented to analyze qualitatively and quantitatively the availability of water in the different segments of the network. Dynamic Bayesian networks (DBN) are then used to assess the valves reliability as function of time, which allows management of water distribution based on water availability assessment in different segments. Finally an application on data of a fraction of a distribution network supplying a town is presented to show the effectiveness and the strong contribution of Bayesian networks (BN) in this research field.

Water Microgrids: The Future of Water Infrastructure Resilience

Microgrids have recently come into vogue as a potential solution to address the increasing number of power outages caused by extreme weather events that impact our cities and communities. Such events – often precipitated by increasing global temperatures and climate change – have repercussions that expand beyond damages to a city's electric infrastructure. Water infrastructure is similarly vulnerable to extreme weather events, resulting in significant impacts to clean water distribution, wastewater treatment, and stormwater management. Given this similarity, and other value drivers to be outlined, this paper proposes leveraging concepts behind electricity microgrids to develop a unified framework for microgrid application to promote water resilience in the face of our changing climate.Many parallels can be drawn between the electric grid and water infrastructure considering both are utilities that generate, store, and distribute an essential product that has been identified as a basic human right. Also similar to the electric grid, water infrastructure is aged and costly to redevelop. For both industries, microgrids are a potential solution that addresses aged infrastructure concerns while also being potentially more cost effective. In addition, by leveraging legacy infrastructural components while developing a new system within the system, microgrids provide redundancy, fortify vulnerabilities and secure the resource supply chain. This paper will investigate parallel components of electric and water infrastructure to provide a vision for future resilient water microgrids.

Applications of Deep Learning for Smart Water Networks

Abstract Deep Learning (DL) is the state-of-art paradigm of Artificial Neural Network (ANN) computing. It is a new breakthrough in machine learning, and differentiates from the conventional or shallow learning algorithms by emulating the six-layer human neocortex, which is unique for human brain containing billions of interconnected neurons. Unlike canonical ANN, DL is capable of self-learning data features by mimicking the self-learning functions layer by layer in human cortex and creating a data-driven model with the given dataset. This paper reports the initial applications of deep learning for simulation, optimization and operation control of water distribution systems. It elaborates the development of efficient deep learning framework with potential applications of facilitating the data fusion, system simulation and predictive analysis, detection of abnormal events from the recorded time series data (pressures, flows and consumptions etc.), water usage prediction, construction of a meta-model as a surrogate to the physics-based models (hydraulic and water quality), and acceleration of the solution search for smart water distribution management, which aims at improving operation efficiency, reducing carbon footprint, and exceling customers’ expectation.

Smart meters for enhanced water supply network modelling and infrastructure planning

To design water distribution network infrastructure, water utilities formulate daily demand profiles and peaking factors. However, traditional methods of developing such profiles and peaking factors, necessary to carry out water distribution network modelling, are often founded on a number of assumptions on how top-down bulk water consumption is attributed to customer connections and outdated demand information that does not reflect present consumption trends; meaning infrastructure is often unnecessarily overdesigned. The recent advent of high resolution smart water meters allows for a new novel methodology for using the continuous ‘big data’ generated by these meter fleets to create evidence-based water demand curves suitable for use in network models. To demonstrate the application of the developed method, high resolution water consumption data from households fitted with smart water meters were collected from the South East Queensland and Hervey Bay regions in Australia. Average day (AD), peak day (PD) and mean day maximum month (MDMM) demand curves, often used in water supply network modelling, were developed from the herein created methodology using both individual end-use level and hourly demand patterns from the smart meters. The resulting modelled water demand patterns for AD, PD and MDMM had morning and evening peaks occurring earlier and lower main peaks (AD: 12%; PD: 20%; MDMM: 33%) than the currently used demand profiles of the regions’ water utility. The paper concludes with a discussion on the implications of widespread smart water metering systems for enhanced water distribution infrastructure planning and management as well as the benefits to customers.

Optimal Localization of Pressure Reducing Valves in Water Distribution Systems by a Reformulation Approach

Leakage reduction represents one of the most challenging tasks in managing water distribution systems (WDSs). An effective way to leakage reduction is to carry out network operational pressure management through optimizing locations and regulations for pressure reducing valves (PRVs) and system pressures. This leads to a mixed-integer nonlinear program (MINLP) with a large number of binary variables which make it difficult to solve by an available software package. In this study, instead of directly solving the MINLP problem, we reformulate it to a mathematical program with complementarity constraints which can be efficiently solved by available NLP algorithms. The binary variables are replaced by continuous ones with complementarity constraints to be satisfied by a penalization scheme. To improve the quality of the solution and also to accelerate the convergence, in each relaxed NLP the results of the binary variables are rounded to binary values with which the NLP problem is solved again to achieve a MINLP solution. The final solution will be determined by the best one among the MINLP solutions. The results from two case studies reveal new and better combinations of PRVs as compared with those given in the literature.

Information and Communication Technologies: An Agent of Social Change for Rural Women in Odisha

Information and Communication Technologies (ICTs) have ushered in the new era and possess the prospective to generate educational and job opportunities, awareness on the basic available health care facilities, legal provisions, government programmes and welfare schemes etc. The benefits amassed from the combination of knowledge and ICT should not be confined to the upper strata of the society but need to liberally flow to all the sections of the female population. The extent of areas in which ICT can put a larger control in the hands of women is extensive and constantly increasing, from managing water distribution at the village-level to standing for local elections and having admittance to enduring learning opportunities. With such an unmatched prowess, ICTs definitely can bring a social change in the rural hinterlands of Odisha, a state in India. A large portion of rural women in the state are reeling under poverty and lack awareness. They are absorbed in the farm sector (which doesn’t promise a hefty return, always) and are unskilled manual laborers. The socio cultural barriers discourage their public participation and decision making ventures. Socially, majority of women in rural Odisha are tied up by age-old traditions. Disparity in women's access to and participation in all communication systems as well as lack of mobilization proves to be a roadblock in their emancipation. It is in this context that this paper wants to examine the underpinning dynamism of culture and technology and if the former fosters or hinders ICT penetration in rural areas of Odisha.

Spatial Approach on Determination of Irigation Priority Area on Dry Seasion

Sawah tanaman padi di daerah utara Jawa Barat bagian utara merupakan salah satu lumbung padi nasional. Sumber pengairan atau irigasi tanaman padi bagian utara Jawa Barat sebagian besar bersumber dari aliran sungai citarum yang masuk ke waduk jatiluhur dan disalurkan dengan saluran irigasi ke daerah irigasi utara Jawa Barat. Pengelolaan distribusi air perlu memperhatikan prioritas lahan irigasi agar memperoleh hasil yang maksimal. Sistem Informasi Geografis (SIG) dapat berfungsi sebagai metode yang dapat digunakan untuk mengolah data yang berbasis spasial atau keruangan. Pendekatan SIG dan kebencanaan menjadi salah satu pendekatan yang dapat menjadi alternatif penentuan prioritas irigasi pada sawah padi. Musim kemarau di Indonesia sering mengakibatkan beberapa wilayah terjadi bencana kekeringan yang tidak terkecuali pada lahan sawah. Kekeringan juga mengakibatkan gagal panen yang menjadikan berkurangnya produksi padi di Indonesia. Pendekatan dan faktor bencana kekeringan dapat menjadi salah satu faktor pertimbangan dalam penentuan prioritas irigasi sehingga dapat memaksimalkan sistem irigasi. Hasil yang didapatkan dari penelitian ini adalah peta area prioritas irigasi di wilayah utara Jawa Barat. Hasil penelitian adalah diketahui prioritas pertama irigasi lahan sawah seluas 9.385,87 ha.

Time-series analysis of monthly rainfall data for the Mahanadi River Basin, India

Time series analysis has two goals, modeling random mechanisms and predicting future series using historical data. In the present work, a uni-variate time series autoregressive integrated moving average (ARIMA) model has been developed for (a) simulating and forecasting mean rainfall, obtained using Theissen weights; over the Mahanadi River Basin in India, and (b) simulating and forecasting mean rainfall at 38 rain-gauge stations in district towns across the basin. For the analysis, monthly rainfall data of each district town for the years 1901-2002 (102 years) were used. Theissen weights were obtained over the basin and mean monthly rainfall was estimated. The trend and seasonality observed in ACF and PACF plots of rainfall data were removed using power transformation (α=0.5) and first order seasonal differencing prior to the development of the ARIMA model. Interestingly, the ARIMA model (1,0,0)(0,1,1) 12 developed here was found to be most suitable for simulating and forecasting mean rainfall over the Mahanadi River Basin and for all 38 district town rain-gauge stations, separately. The Akaike Information Criterion (AIC), goodness of fit (Chi-square), R 2 (coefficient of determination), MSE (mean square error) and MAE (mea absolute error) were used to test the validity and applicability of the developed ARIMA model at different stages. This model is considered appropriate to forecast the monthly rainfall for the upcoming 12 years in each district town to assist decision makers and policy makers establish priorities for water demand, storage, distribution, and disaster management.

Water Distribution and Paddy Field Management in a Part-time-Farmer-Dominant Paddy Rice Area

Water Distribution and Paddy Field Management in a Part-time-Farmer-Dominant Paddy Rice Area

Pricing of irrigation water under alternative charging methods: Possible shortcomings of a volumetric approach

The European water framework directive aims to protect the environmental quality of water and encourage its efficient use. EU member states are required to implement efficient water management systems and appropriate water-pricing methods. This paper examines the economic effects that may arise given the introduction of two different methods for pricing irrigation in the Mediterranean area. The considered pricing methods charge farmers for the costs incurred by water user associations (WUAs) in managing water distribution networks. The first method, based on the metered use of water by farms, is known as the volumetric pricing method. The second is an area-based pricing method, whereby fees are charged per hectare according to the estimated average water use for each crop. The economic effects and the impacts on the water usage of these two schemes are analyzed using a mathematical model that represents the farm sector in a Mediterranean area that relies on a dam for irrigation. The possible effects are analyzed under two scenarios: first, the methods are applied to the observed water-pricing conditions, second, an additional charge is introduced to recover unaccounted costs of the water supply system (e.g., long-term costs related to infrastructure, and the operational and maintenance costs of dams) in line with the water framework directive principle of cost recovery. The results show that the introduction of an additional charge via the volumetric pricing method could stimulate the substitution of water provided via collective networks with groundwater. This could adversely affect the financial situation of the WUA and have negative environmental consequences. This negative outcome does not arise in the case that an additional charge is applied via the area-based pricing method.

Vers l'institutionnalisation d'une délégation communautaire ?

This paper investigates the potential segmentation and building of hybrid management systems for urban water utilities in low-income countries. It analyses a unique water supply experiment for poor urban settlements in the city of Port-au-Prince, which combined a bulk water meter connection to the public water network and delegated management of water distribution to the local community. Using neo-institutional economics as a reference, the paper analyses implemented tools, as well as the processes and progressive methods applied which allowed for the institutional establishment and stabilization of this hybrid system. Finally, the paper highlights the limitations of institutional sustainability for the establishment of the water utility in the context of a weak state, further exacerbated in the aftermath of the devastating earthquake which occurred on the 12th January, 2010.

엔트로피 이론을 이용한 상수관망의 최적 압력 계측 위치 결정

Determination of optimal pressure monitoring location is essential to manage water distribution system efficiently and safely. In this study, entropy theory is applied to overcome defects of previous researches about determining the optimal sensor location. The previous studies required the calibration using historical data, therefore, it was difficult to apply the proposed method in the place where the enough data were not available. Also, most researches have focused on the locations to minimize cost and maximize accuracy of the model, which is not appropriate for the purpose of maintenance of the water distribution system. The proposed method in this study quantify the entropy which is defined as the amount of information calculated from the pressure change due to the variation of discharge. When abnormal condition is occurred in a node, the effect on the entire network is presented by the entropy, and the emitter is used to reproduce actual pressure change pattern in EPANET. The optimal location to install pressure sensors in water distribution system is the nodes having the maximum information from other nodes. The looped and branched networks are evaluated using the proposed model. As a result, entropy theory provides general guideline to select the locations to install pressure sensors and the results can be used to help decision makers.

Local transformation of a state‐initiated institutional innovation: The example of water users' associations in an irrigation scheme in Morocco

AbstractThe international debate on participatory management and irrigation management transfer has mainly focused on ex‐ante/ex‐post evaluations that rely on quantitative performance indicators to measure the failure or success of management transfer and the functioning of water users' associations (WUAs). This article focuses on the appropriation by farmers of state‐initiated WUAs illustrated by the case of the Moyen Sebou irrigation scheme in Morocco. This scheme, which was designed for agency‐managed water distribution, was implemented at the height of the debate on participatory management in the early 1990s, and was transformed into a farmer‐managed irrigation scheme. The results revealed the gradual adoption of the water institutions (WUAs and the federations of WUAs) by farmers, who continuously crafted and adapted rules for the management of water distribution, collection of water fees, and governance of the irrigation scheme. In addition, there were a number of indirect spin‐offs generated by the collective learning process in terms of leadership, collective action, local democracy and local development. Copyright © 2009 John Wiley & Sons, Ltd.

Low Pt Thin Cathode Layer Catalyst Layer by Reactive Spray Deposition Technology

National Research Council Canada's Institute for Fuel Cell Innovation, NRC-IFCI, has been developing the Reactive Spray Deposition Technology (RSDT) process to optimize composite electrode layer formation and develop novel electrocatalysts and catalyst layers. The RSDT process provides the means necessary to develop the next generation of thin, low platinum or alloy catalyst layers for PEM MEA's. In order to best manage water distribution, mass transport and conductivity, the structure should be a gradient with controlled porosity and controlled distribution of both platinum and ionomer across the catalyst layer. The RSDT process allows good control of the platinum particle size as they are created directly from metal vapors, which prevents agglomeration in the catalyst layer. Additionally, it has the flexibility to build a gradient layer structure across a very thin film catalyst layer (<1 um). In our design, a platinum sub-layer (100 nm) was deposited directly on a Nafion® 117 membrane as a columnar structure. After the sub-layer, the platinum loading was reduced in a co-deposited layer of Pt-Nafion (ionomer)-carbon with the lowest loading closest to the GDL. The combined loading of both layers was <0.05mg/cm2 Pt with this approach. The manufactured catalyst layer has a performance of 0.65V at 1 A/cm2 with 0.05mg/cm2 Pt loading using pure oxygen .

Logística de distribuição de água em redes urbanas: racionalização energética

O problema estudado neste trabalho visa minimizar o custo de energia elétrica necessário para a operação de bombas hidráulicas, que captam água de poços artesianos para os reservatórios distribuídos em bairros da cidade, de onde a população é atendida. Como o custo da energia elétrica varia ao longo do dia, se faz necessário um planejamento da operação das bombas e armazenamento de água no sistema. Um modelo de otimização linear inteira é proposto para o problema, considerando um custo de partida das bombas. Desconsiderando esse custo, as variáveis binárias do modelo são eliminadas e um segundo modelo de otimização linear é também analisado. Algumas instâncias geradas aleatoriamente são resolvidas e suas soluções analisadas, demonstrando que os modelos propostos oferecem suporte gerencial consistente para seu uso no problema real.