Real Water Distribution Network Research Articles

A Pragmatic Approach for Chlorine Decay Modeling in Multiple-Source Water Distribution Networks Based on Trace Analysis

Providing water with adequate quality to users is one of the main concerns for water utilities. In most countries, this is ensured through the introduction of disinfectants, such as chlorine, which are subjected to decay over time, with consequent loss of disinfection action and the possible formation of harmful by-products. In this context, water quality models can be a useful tool to support management and, thus, ensure sufficient standards in all network points, but most of these models require the input of reaction parameters which could be difficult to obtain based on the information available to water utilities, especially in the case of complex water distribution networks (WDNs) supplied by more than one source. This study proposes a pragmatic, interval-number-based method to model chlorine decay in complex WDNs by relying on the use of the network hydraulic model and the results of trace analysis, which are exploited to obtain overall reaction rates. The method is applied to the case of a real WDN supplied by water sources with different qualitative features. The results obtained highlight that the method can help water utilities in the identification of overall water quality parameters.

Markov decision process based value chain calculation of water distribution network scheduling

Precise value of scheduling decisions forms the cornerstone of water distribution network (WDN) scheduling optimization, which aims at conserving energy and enhancing network operational efficiency. This article proposes a computational methodology for evaluating the value chain of scheduling decisions in WDN. The scheduling process is modeled as a Markov decision process with immediate reward function, action and state space. Due to the periodicity of water supply and sequential nature of scheduling, the calculation quantifies cumulative value of scheduling decisions by incorporating state transition probability with expected value. The effectiveness and applicability of the proposed evaluation method are demonstrated using scheduling data from a real world WDN. The method provides rational values on scheduling period and strategies, offering practical feedback for scheduling decisions.

Intelligent real-time scheduling of water supply network based on deep learning

Abstract Inappropriate scheduling plans can result in additional economic losses and the safety of water distribution network (WDN). Optimizing manual experience based scheduling plans can help water utilities rationally allocate water plants and pump stations, ensuring the safety, stability, and economy of the water supply system. However, there is a lack of real-time, rational, and optimized scheduling methods. To address this, we proposed a novel intelligent scheduling framework based on deep learning. In this framework, two neural network models, multi-heads convolutional gated recurrent unit network (MH-CGRU) and multi-head gated recurrent unit network (MH-GRU), can effectively extract key features from the WDNs. Operating data were used as decision variables to predict and generate scheduling orders for water plants and pump stations, respectively. The rationality of the orders is verified by combining a high precision online hydraulic model and the evaluation of the operational status of the WDNs. This system has been deployed in a real WDN and put into practical application. From June to November of 2022, the total adoption rate of all orders reached 96.29%, with the average deviation between predicted and actual control targets being less than 5%, and energy consumption decreased by 3.05% compared to the previous year.

Equitable supply in intermittently operated rural water networks in emerging economies

Abstract Many operators of water distribution networks (WDNs) are unable to meet the increasing demand for water. Utility operators in such situations resort to rationing the supply as a partial solution to this problem; this, in turn, may lead to disproportionate allocation of water or inequity in supply. In this study, we propose a mixed integer non-linear program formulation and an efficient solution approach to minimize the inequity in supply, subject to hydraulic constraints and additional constraints on hours of supply and valve operation. Further, we show that the schedule can be obtained using a data-driven approach based on flow and level measurements, which eliminates the modelling effort and uncertainty associated with the use of hydraulic models. We demonstrate the proposed approaches through simulations of a real WDN, and experiments conducted on a topologically similar laboratory-scale network.

Application of pressure reducing and throttle control valves for optimal pressure management in water distribution networks

ABSTRACT Advanced pressure control facilitates the smart management of water distribution networks (WDNs). In this study, an optimization-based method is proposed to develop a time-based schedule for pressure reducing valves (PRVs). For this purpose, a single-objective optimization problem is initially delineated, seeking to minimize spatiotemporal variations in the nodal pressures. Then, the application of PRVs is addressed in two scenarios, viz. individual (i.e. employing PRVs) and hybrid (i.e. the combined use of PRVs and throttle control valves [TCVs]). The proposed scenarios are subsequently applied to the hydraulic model of synthetic and real WDNs. A set of hydraulic evaluation indices, including variation index (VI), are further measured to spot the optimal pressure management scenario. The study results establish that the hybrid scenario leads to a larger decrease in the VI along with more efficient pressure control (namely, 39.9% and 11.8% in the synthetic and real WDNs, respectively), compared with the individual one.

Formation of disinfection by-products within the drinking water production system and distribution network of a real case study

This work presents a collaboration between the so-called Gasset Service Association (responsible for providing drinking water to 100,000 inhabitants from a surface water reservoir) and researchers from the University of Castilla-La Mancha (Spain). The main aim of this work was providing a comprehensive characterization of the formation and removal of disinfection by-products in a real drinking water treatment plant (DWTP) and water distribution network. According to the results obtained, it can be stated that bromate is formed on the pre-oxidation stage and it is not eliminated throughout the DWTP; meanwhile, total organic carbon is partially removed on the clarification process. Moreover, it demonstrates the key role of the residence time and the type of water storage throughout the distribution network (either in pipes or in tanks) due to the combined effect of, at least, four overlapped mechanisms: THMs chemical generation, air stripping, hydrolysis and biological removal. This comprehensive view of the drinking water production and distribution network represents an excellent framework for allowing the improvement in the drinking water quality for a very common water production case study: a medium-size city fed by a surface water source.

Performance evaluation of ANN and ANFIS models for estimating velocity and pressure in water distribution networks

Abstract In this study, two artificial intelligence techniques: (1) artificial neural networks (ANNs) using different algorithms such as Lavenberg–Marquardt (LM), Bayesian Regularization (BR), and Scaled Conjugate Gradient (SCG) and (2) Adaptive Neuro-Fuzzy Inference System (ANFIS) are used to predict velocity and pressure for Gadhra (DMA-5) real water distribution network (WDN), East Singhbhum district of Jharkhand, India. In case 1, flow rate and diameter are used as independent variables to predict velocity. In case 2, elevation and demand are used as independent variables to predict pressure. 80% of the data are used to train, test, and validate the ANN and ANFIS prediction models, while 20% of the data are used to evaluate data-driven models. Sensitivity analysis is performed in ANN-LM to understand the relationship between the independent and dependent variables. The performance indices of RMSE, MAE, and R2 are evaluated for ANN and ANFIS for different combinations. The ANN-LM, with 2-16-1 architecture, is found as a superior to predict velocity and ANN-LM with architecture 2-17-1 is found as a superior to predict pressure. ANN-LM had the best prediction in estimating velocity (RMSE = 0.0189, MAE = 0.0122, R2 = 0.9568) and pressure (RMSE = 0.3244, MAE = 0.2176, R2 = 0.9773).

Energy Recovery Optimization by Means of a Turbine in a Pressure Regulation Node of a Real Water Network Through a Data-Driven Digital Twin

In recent years, various devices have been proposed for pressure regulation and energy recovery in water distribution and transport networks. To provide a real net benefit, they require a dedicated long-distance management system in order to carry on both hydraulic regulation and electricity production without direct human manual operations. This work presents a new proposal for the management of a pressure regulation system based on the PRS turbine. The proposal is applied to a real water distribution network, named Montescuro Ovest pipeline, at the San Giovannello station. The Real Time Control (RTC) logic currently applied at San Giovannello station is first presented and discussed. A new Advanced Real Time Control (ARTC) logic is then proposed, based on direct configuration of the turbine and the surrounding valves as computed by the solution of an optimization problem. In ARTC a digital twin, including the hydraulic model of the surrounding network, provides a one-to-one relationship between the configuration parameters and the state variables, i.e. flow rates and pressures. The digital twin model equations are continuously updated on the basis of the recorded measures. Besides providing almost identical performance to the current RTC logic in the current operational scenario, the improved ARTC is more robust, in that it guarantees better hydropower generation in modified operational scenarios, as shown in specific tests. The proposed methodology constitutes a new approach to regulating the valves in hydroelectric plants which are currently regulated with traditional automation algorithms.

HYPER: Computer-Assisted Optimal Pump-as-Turbine (PAT) Selection for Microhydropower Generation and Pressure Regulation in a Water Distribution Network (WDN)

Although pressure reducing valves (PRVs) have traditionally been employed to regulate pressure and reducer water leakage, researchers have been increasingly investigating the strategy of micro-hydropower generation using pumps as turbines (PATs) to enable both pressure reduction and energy production as an alternative strategy in water distribution networks (WDNs). However, due to the continuous variability of flow discharge during the day, selecting the optimal PAT remains a challenging issue. To address this, the authors have developed HYPER, a freely available software app that implements an innovative approach for selecting the most suitable PAT in systems that involve both hydraulic and/or electrical regulation. In enabling the identification of the PAT parameters that maximize energy production, HYPER thus provides a fast and effective PAT selection tool. The effectiveness of the proposed approach was further demonstrated with application to a real WDN. Four operational patterns varying in terms of available flow and head drop were considered, showing that the most efficient pumps consistently tended to be located in close proximity to the maximum produced energy. Furthermore, the results confirmed that hydraulic regulation and coupled hydraulic/electric regulation-based installation layouts represent the best solutions in terms of energy produced. The solely electrical regulation option, given its poor flexibility, returns in all cases lower energy production with the lower adaptability of commercial pumps.

State‐of‐the‐art review of leak diagnostic experiments: Toward a smart water network

AbstractEffective water pipeline leak detection and localization can help water practitioners save water losses and reduce pipe rehabilitation budgets. Different sensing technologies can provide essential data aiding model development for predicting future leaks in the water distribution networks. Solutions for applying different sensing technologies to real water distribution networks are being developed for real‐time data collection, precise leak localization, reducing false alarms, and continuous pipeline monitoring. Experiments of different scales and specifications have been conducted to test the application and effectiveness of sensing technologies for leak diagnosis in water pipelines. Quality data collection is especially crucial for the successful implementation of these experiments. However, practitioners need help designing effective leak detection and localization experiments, wasting time, and resources. There needs to be a greater understanding of the design parameters for more accurate testing, such as sensor selection, sensor placement, ambient noise sources, and system operations. The current study, therefore, delineates design parameters for design leak diagnosis experiments for lab, testbed, and real networks. For application in real water networks, expert opinion is used to help identify the benefits and limitations and the implementation issues of available sensing technologies. An example experiment design using multi‐sensing technologies for smart leak diagnostics in Hong Kong is also presented. The study can guide water practitioners and researchers to design a multi‐sensing leak diagnostic experiments enabling a smart and sustainable utility management.This article is categorized under: Engineering Water > Methods Engineering Water > Sustainable Engineering of Water Science of Water > Water Extremes

Integrated Smart Management in WDN: Methodology and Application

Urbanization and population growth have been responsible for a significant increase in consumption of water and energy at a global scale. A careful management of water resource and infrastructures is crucial for Energy Transition, as well as for achieving a sustainable efficiency of these systems. High pressure values along with the ageing of the systems contribute to high leakage levels of Water Distribution Networks (WDN). The simultaneous control of excess pressure and containment of water losses are mainly performed by using Pressure Reducing Valves (PRVs) in WDN, which dissipate the surplus of hydraulic energy. Instead of being dissipated, energy can be recovered by the transformation of the excess pressure into electrical energy with the use of Pump as Turbines (PAT), which results in an increased reliability, reduction of cost and an overall improvement in the efficiency of WDN. The work aims on presenting an integrated efficiency management methodology in terms of Effectiveness (E), capability (ηpi), reliability (μpi) and sustainability (χpi) with values between 47 to 98%, also associated with the pressure and leakage management, and energy recovery. This research presents a modelling of a real WDN of a District Metering Areas (DMA) of Beloura endowed with seasonal consumption variability to better show its applicability. Additionally, an economic analysis to assess the solution’s feasibility is presented concluding an annual energy recovered of 9.8 MWh and a saving of about 30% of water leakage, which correspond, in the analyzed case study, to about 3523 m3. The payback period found is around 9 or 12 years, for only one PAT or two different PATs installed, due to the small available energy of the analyzed case study. Acknowledging the synergy between water and energy efficiency and taking advantage of these integrated smart management methodology exemplification, it resulted in more efficient systems to achieve both effectiveness solutions, digital and energy transition in the water sector.

Hyperparameter Optimization of a Convolutional Neural Network Model for Pipe Burst Location in Water Distribution Networks

The current paper presents a hyper parameterization optimization process for a convolutional neural network (CNN) applied to pipe burst locations in water distribution networks (WDN). The hyper parameterization process of the CNN includes the early stopping termination criteria, dataset size, dataset normalization, training set batch size, optimizer learning rate regularization, and model structure. The study was applied using a case study of a real WDN. Obtained results indicate that the ideal model parameters consist of a CNN with a convolutional 1D layer (using 32 filters, a kernel size of 3 and strides equal to 1) for a maximum of 5000 epochs using a total of 250 datasets (using data normalization between 0 and 1 and tolerance equal to max noise) and a batch size of 500 samples per epoch step, optimized with Adam using learning rate regularization. This model was evaluated for distinct measurement noise levels and pipe burst locations. Results indicate that the parameterized model can provide a pipe burst search area with more or less dispersion depending on both the proximity of pressure sensors to the burst or the noise measurement level.

Selecting the best location of water quality sensors in water distribution networks by considering the importance of nodes and contaminations using NSGA-III (case study: Zahedan water distribution network, Iran).

One of the most effective ways to minimize polluted water consumption is to arrange quality sensors properly in the water distribution networks (WDNs). In this study, the NSGA-III algorithm is developed to improve the optimal locations of sensors by balancing four conflicting objectives: (1) detection likelihood, (2) expected detection time, (3) detection redundancy, and (4) the affected nodes before detection. The research procedure proposed the dynamic variations of chlorine between defined upper and lower bounds, which were determined utilizing the Monte Carlo simulation model. For selecting a contamination matrix with the same characteristics and effects of all possible events, a heuristic method was applied. The coefficients of importance are introduced in this study for the assessment of contamination events and network nodes. The Pareto fronts for each of the two sets of conflicting objectives were computed for benchmark and real water distribution networks using the proposed simulation-optimization approach. Results indicated that sensors should be installed downstream of the network to maximize sensor detection likelihood; however, this increases detection time. For the benchmark network, maximum and minimum detection likelihoods were calculated as 92.8% and 61.1%, respectively, which corresponded to the worst detection time of 11.58min and the best detection time of 5.06min. So, the position of sensors regarding the two objective functions conflicts with each other. Also, the sensitivity analysis related to the number of sensors illustrated that the Pareto fronts became a more efficient tool when the number of sensors increased. The best pollution detection likelihood in the real water network increased by 18.93% and 24.66% by incrementing the number of sensors from 5 to 10 and 5 to 15, respectively. Moreover, adding more than 10 sensors to the benchmark network and more than 15 to the real system will provide little additional detection likelihood.

Using WDN-tailored complex network centrality metrics to assess isolation valve system reliability

Mechanical reliability Water Distribution Networks (WDNs) depends on the Isolation Valve System (IVS). In fact, in the event of accidental disruptions or planned maintenance works, segments of the WDNs need to be temporarily disconnected by closing isolation valves to allow pipes repair. This maneuver it modifies the WDN topology and relevant hydraulic behavior. In this paper a recent approach for IVS reliability based on the Complex Network Theory (CNT) has been applied. It couples the construction of the graph of segments and isolation valves generated by the IVS with the risk of segment interruptions, using several WDN-tailored centrality metrics. The study is demonstrated on a real WDN using a Digital Water Service developed ad hoc for enabling technicians and water utilities in targeting the most critical valves in case of failure and thereby defining a lineup for valves inspections and maintenance.

Leakage Management Influence on Water Age of Water Distribution Networks

AbstractLeakage management of Water Distribution Networks (WDNs) is a relevant technical task worldwide. Background leakages along mains and connections to properties in aged infrastructures represent a significant portion of the WDN water outflow, sometimes exceeding customer demands. Pressure control and District Metering Areas (DMAs) design are two classic activities aimed at leakage management. The former reduces the background leakages, and thus the velocities in pipes, especially those along main paths for water transport across the WDN. The latter involves closed valves confining each DMA, which change network connectivity reducing redundancy and eventually pressure, that is, background leakages. Hence, both activities reduce water velocity in pipes because of leakage reduction (i.e., the overall WDN inflow), while DMAs could increase it in some pipes. Therefore, leakage management activities might affect the water age in WDNs, as a general water quality indicator, depending on the initial level of leakages, the WDN connectivity and topology, and the attained reduction. This work studies the effect of leakage management on water age for two real WDNs, which are characterized by different initial levels of leakages and expected reduction, after planning pressure control and DMAs. The advanced hydraulic modeling, employing pressure‐driven leakage modeling at pipe level, is integrated with water age analysis, allowing unlimited number of parcels. The sensitivity of water age to the maximum number of parcels in the model is studied to identify the trade‐off between accuracy and computational runtime. The variation of mean daily water age due to change of demand pattern is analyzed considering a 4‐week operative cycle.

Online Edge Flow Imputation on Networks

An online algorithm for missing data imputation for networks with signals defined on the edges is presented. Leveraging the prior knowledge intrinsic to real-world networks, we propose a bi-level optimization scheme that exploits the causal dependencies and the flow conservation, respectively via <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">(i)</i> a sparse line graph identification strategy based on a group-Lasso and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">(ii)</i> a Kalman filtering-based signal reconstruction strategy developed using simplicial complex (SC) formulation. The advantages of this first SC-based attempt for time-varying signal imputation have been demonstrated through numerical experiments using EPANET models of both synthetic and real water distribution networks.

Frequency-based leak signature investigation using acoustic sensors in urban water distribution networks

Cities worldwide have been plagued by water pipe leaks for many decades, resulting in financial losses, public health risks, and environmental impacts. Current practice still relies heavily on periodic and localized inspection rather than long-term continuous monitoring, and since water pipelines are buried underground, leaks can often go undetected for prolonged periods. Noninvasive acoustic-based methods for continuous pipeline monitoring have gained increasing popularity the past decade thanks to the recent advances in sensing and communication technology. Previous research indicates that hydrophones, in particular, are capable of effectively detecting leak-induced acoustic waves inside a water pipe. However, most studies to date have been limited to either controlled or field test-bed settings; hence, findings might not generalize well to real-world complex pipe networks. Through rigorous leak tests conducted in a real water distribution network and an extensive analysis of the field-collected acoustic signals, the current study aims to test the applicability of low-cost, non-intrusive hydrophones attached to fire hydrants for continuous pipe monitoring and leak detection. Continuous wavelet transform, power spectrum, and band power analyses were employed to identify the leak signature and distinguish normal from leak acoustic data in various leak scenarios. Results indicate that the acoustic signals generated by the simulated leaks in this field study are characterized by a consistent increase in the power of the frequency band 150–450 Hz primarily, whereas background noise levels and conditions significantly vary depending on the location of the sensor in the network. Realistic conditions in urban water distribution networks, including background noise, complicated topology, and varying pipe size and material, are still posing significant challenges for cost-effective and widespread implementation of acoustic-based sensors to achieve continuous monitoring in water pipe networks for leak detection. Even though further research and development is required to handle the highly variable conditions of real systems, the low-cost hydrophones tested in this work demonstrated potential in detecting low-flow leaks in simple and complex pipe topologies.

A complete digital water experience to support real leakage management planning

In the next years digital transition of Water Distribution Networks (WDNs) will represent a long-standing challenge for triggering innovations in the WDNs management tasks. The ongoing impulse for innovation, boosted also by the economic resources for post-pandemic recovery, is opening novel opportunities for technicians and researchers in the context of Digital Water. This work reports the key steps where novel concepts and tools of Digital Water have been used to support consultant companies in designing WDN leakage management actions in a real WDN managed by Acquedotto Pugliese, in Southern Italy. The Digital Water Services (DWSs) were used to support key phases of the workflow, including validation of topological data and integration of georeferenced connection to private properties; calibration of advanced hydraulic model exploiting mass-balance in pressure-driven analysis; the application of strategies for DMA design and pressure control; and the planning of pipe rehabilitation. WDNetXL platform was used to develop WDN Digital Twin and exploit the DWSs. Applying the Digital Water experience to multiple WDNs managed by the same provider also enabled planning the best courses of actions accounting for investments vs. expected leakage reduction at global scale.

Digital Water Services using Digital Twin paradigm

In the last years, the digital transition concept has spread all over public and private life as a process designed for improving problem solving in industry by the combination of models, information, and connectivity technologies. In the Water Distribution Networks (WDNs) management sector, the innovations in the areas of ICT/IoT, virtual representation of infrastructure elements in GIS/BIM platforms and the advancements in hydraulic modelling offer the opportunity to open a new era for water engineering. Nonetheless, a unique consensus about the digital transformation meaning in WDNs management is still missing. In this paper a recent paradigm for the digital transformation for WDNs is exposed and further extended, starting from the concept of Digital Twin for WDNs management. It encompasses the virtual representation of features and devices of the network integrated with advanced hydraulic modelling and Artificial Intelligence for supporting WDNs management tasks. The WDN Digital Twin is used within tools, named Digital Water Services (DWSs), working on GIS platforms. DWSs are conceived to support distinct phases of WDNs management by improving engineering awareness on technical decisions. Several DWSs, previously adopted for real WDNs management and planning, are here presented, as support tools for technicians and water utilities for achieving short-term and long-term management tasks.

Geolocalization of water-waves origin within water distribution networks using time reversal of first event detection

Drinking water distribution networks in urban areas are daily subject to fast propagating pressure waves resulting from routine operations. These water-hammer waves lead to structural aging and facility damages, the origin of which is not easy to find but are sometimes of high managerial interest. In this contribution, we demonstrate that using a reasonable number of high-frequency pressure detectors distributed within the network combined with a proper post-processing method permits a close geolocalization of the damaging wave origin. The method is first tested and validated on a real water distribution network having approximately 26000 pipes, whereas considering a known, prescribed waveorigin, so that the sensitivity to sensor number (sensor spatial density), sensor location and signal-to-noise ratio on the geolocalization robustness are analyzed in detail. It is then applied and illustrated over real sensor recordings the result of which are validated on the field from history matching. This paper thus presents the first field-scale geolocalization of water-hammer events origin test as well conditions for which, given sensor density and signal-to-noise ratio, the geolocalization success is to be expected.