Management Of Water Distribution Systems Research Articles

Bibliometric Analysis of Risk Management of Water Distribution System

This study aims to provide valuable insights that can contribute to future research directions, policy formulation, and management of water distribution systems to avoid potential risks. This research was conducted using bibliometric analysis of articles related to the topic under study. This research methodology is designed to carry out bibliometric analysis of literature related to water distribution systems, using the VOSviewer and Publish or Perish 8 applications. Research findings show that passenger transportation, satisfaction, and development are the three main keywords and additional keywords related to the research topic. Based on data from the Public Transportation Satisfaction Study, it can be concluded that the number of studies continues to increase from 2000 to 2023, with the highest number in 2021. The research trend regarding public transportation satisfaction continues to grow every year and will continue to increase in the coming years.

Energy Optimization in Water Distribution System and Pump Scheduling

Efficient management of water distribution systems are critical for providing consistent water supply while reducing energy usage and operational expenses. This research proposes a unique method for improving water distribution and pump scheduling. The suggested system leverages ultrasonic sensors to monitor water levels in storage tanks, then dynamically changes pump operation and valve settings depending on real-time demand and tank levels. A mobile application gives users remote access to system controls, allowing them to work from anywhere. By combining sensor data with intelligent algorithms, the system optimizes pump scheduling to fulfill water demand while conserving energy and lowering system losses. The creation and implementation of such a system have tremendous potential to improve the performance and sustainability of water distribution networks.

Water Distribution Systems: Integrated Approaches for Effective Utility Management

An extensive review of research advances in distribution system management was conducted to include methods, tools, and frameworks for integration. Sources included archival journals and water industry reports from research institutes, government regulators, and industry media covering case studies of advances that were implemented. Results showed that while effective management of water distribution systems requires an integrated approach, none of the available frameworks for one are in broad use in the water supply industry. Frameworks developed include a management standard of the American Water Works Association and Distribution System Optimization, a methodology for physical, hydraulic, and water quality performance assessment. The intelligent systems framework also offers a promising pathway to integration, but it lacks a definite structure. The voluntary aspect of adopting innovations within the fragmented and uncoordinated nature of the water utility industry poses a barrier to adoption of such innovations. Another barrier is the uncoordinated arrangements of water research stakeholders with different incentive structures. Intelligent water systems offer a way to incentive the utility industry to encourage implementation. They can provide a bottom-up approach where the utility industry can see advantages, as opposed to a top-down approach where they are expected to adopt a method without seeing clear benefits. Research to develop new and improved tools is needed, but the research roadmap should prioritize implementation.

Delay and Energy Efficient Offloading Strategies for an IoT Integrated Water Distribution System in Smart Cities

In the fast-moving world of information and communications technologies, one significant issue in metropolitan cities is water scarcity and the need for an intelligent water distribution system for sustainable water management. An IoT-based monitoring system can improve water distribution system management and mitigate challenges in the distribution network networks such as leakage, breakage, theft, overflow, dry running of pumps and so on. However, the increase in the number of communication and sensing devices within smart cities has evoked challenges to existing communication networks due to the increase in delay and energy consumption within the network. The work presents different strategies for efficient delay and energy offloading in IoT-integrated water distribution systems in smart cities. Different IoT-enabled communication network topology diagrams are proposed, considering the different water network design parameters, land cover patterns and wireless channels for communication. From these topologies and by considering all the relevant communication parameters, the optimum communication network architecture to continuously monitor a water distribution network in a metropolitan city in India is identified. As a case study, an IoT design and analysis model is studied for a secondary metropolitan city in India. The selected study area is in Kochi, India. Based on the site-specific model and land use and land cover pattern, delay and energy modeling of the IoT-based water distribution system is discussed. Algorithms for node categorisation and edge-to-fog allocation are discussed, and numerical analyses of delay and energy models are included. An approximation of the delay and energy of the network is calculated using these models. On the basis of these study results, and state transition diagrams, the optimum placement of fog nodes linked with edge nodes and a cloud server could be carried out. Also, by considering different scenarios, up to a 40% improvement in energy efficiency can be achieved by incorporating a greater number of states in the state transition diagram. These strategies could be utilized in implementing delay and energy-efficient IoT-enabled communication networks for site-specific applications.

Water Distribution System Management in District Metered Area (DMA) Kalipuro 5

Water supply system is an important infrastructure that needs improvement in water distribution networks efficiency, along with energy consumption and water losses. DMA Kalipuro 5 is formed to  improve the management of water distribution system by monitoring the water flows into the district. This program is supported by pressure management, repairs, active leakage control, and asset management. Water balance is the first step to reduce the water losses. From the water balance of DMA Kalipuro 5 calculated in January and September 2022, the percentage of water losses decreases 7,02%, from 62,55% to 55,53%. The percentage of physical water losses also decreases 7,06%, from 62,32% to 55,26%. Pressure management is conducted in order to reduce the physical water losses by installing pressure reducing valve (PRV). From the simulation of existing water distribution network, installing PRV can reduce the highest pressure from 108,82 meters to 58,42 meters.

Deep fuzzy mapping nonparametric model for real-time demand estimation in water distribution systems: A new perspective.

Hydraulic modeling has been recognized as a valuable tool for improving the design, operation, and management of water distribution systems (WDSs) as it allows engineers to simulate and analyze behaviors of WDSs in real time and help them make scientific decisions. The informatization of urban infrastructure has motivated the real-time fine-grained control of WDSs, making it one of the hotspots in recent years, thereby putting higher requirements on WDS online calibration in terms of efficiency and accuracy, especially when dealing with large-complex WDSs. To achieve this purpose, this paper proposes a novel approach (i.e., deep fuzzy mapping nonparametric model (DFM)) from a new perspective for developing a real-time WDS model. To our knowledge, this is the first work that considers uncertainties in modeling problems using fuzzy membership functions and establishes the precise inverse mapping from pressure/flow sensors to nodal water consumption for a given WDS based on the proposed DFM framework. Unlike most traditional calibration methods that require time to optimize model parameters, the DFM approach has a unique analytical solution derived through rigorous mathematical theory, thus the DFM is computationally fast as a result of sensibly handling the problems whose solutions typically require iterative numerical algorithms and large computational time. The proposed method is applied to two case studies and the results obtained show that it can produce a real-time estimation of nodal water consumption with higher accuracy, computational efficiency, and robustness relative to traditional calibration methods.

Machine-Learning-Based Health Monitoring and Leakage Management of Water Distribution Systems

The reduction of pipe leakage is one of the top priorities for water companies, with many investing in greater sensor coverage to improve the forecasting of flow and detection of leaks. The majority of research on this topic is focused on leakage detection through the analysis of sensor data from district metered areas (DMAs), with the aim of identifying bursts after occurrence. This study is a step towards development of ‘self-healing’ water infrastructure systems. In particular, the concepts of machine-learning (ML) and deep-learning (DL) are applied to the forecasting of water flow in DMAs at various temporal scales, thereby aiding in the health monitoring of water distribution systems.  This study uses a dataset for ~2500 DMAs in Yorkshire, containing flow time-series recorded at every 15-minute interval over the period of a year. Firstly, the method of isolation forests is used to identify anomalies in the dataset which are verified as corresponding to entries in water mains repair log, indicating the occurrence of bursts. Going beyond leakage detection, this research proposes a hybrid framework of DL models - such as recurrent neural networks (RNNs) and transformer neural networks) - and state-space ML algorithms - such as Kalman filter and autoregressive integrated moving average (ARIMA). The ML algorithms are trained to forecast the stationary component of the expected flow patterns in real-time, which is then combined (through Bayesian updating) with the non-stationary component obtained from DL models. As well as providing expected day-to-day flow demands, this framework aims to issue sufficient early warning for any upcoming anomalous flow or possible leakages. For a given forecast period, the framework can be used to compute the probability of flow exceeding a pre-defined threshold, thus allowing decisions to be made regarding any necessary interventions. This can inform targeted repair strategies which best utilise resources to minimise leakage and disruptions by addressing both detected and predicted burst events.

Assessment of ERA5-Land Data in Medium-Term Drinking Water Demand Modelling with Deep Learning

Drinking water demand modelling and forecasting is a crucial task for sustainable management and planning of water supply systems. Despite many short-term investigations, the medium-term problem needs better exploration, particularly the analysis and assessment of meteorological data for forecasting drinking water demand. This work proposes to analyse the suitability of ERA5-Land reanalysis data as weather input in water demand modelling. A multivariate deep learning model based on the long short-term memory architecture is used in this study over a prediction horizon ranging from seven days to two months. The performance of the model, fed by ground station data and ERA5-Land data, is compared and analysed. Close-to-operative forecasting is then presented using observed data for training and ERA5-Land dataset for testing. The results highlight the reliability of the proposed architecture fed by ERA5-Land data for different time horizons. In particular, the ERA5-Land shows promising performance as input of the multivariate machine learning forecasting model, although some meteorological biases are present, which can be improved, especially in close-to-operative application with bias correction techniques. The proposed study leads to practical implications in the use of regional climate model outputs to support drinking water forecasting for sustainable and efficient management of water distribution systems.

State estimation based on enhanced Bayesian approach: Application in water distribution systems

Hydraulic models have been regarded as an essential tool for controlling and operating water distribution systems (WDSs). With the rapid development of communication networks, real-time control is becoming a hot issue. The nodal water demand as the state variable should be estimated for the control and management of WDS. Due to the lack of sufficient observed data to determine the nodal water demand, the hydraulic model may result in unreasonable model outputs, which are undesirable in actual engineering. We develop a Bayesian inference method to fuse nodal pressure prior information into the state estimation process to address this problem. The developed approach can constrain the nodal water demand estimation process and keep the model outputs (e.g., nodal water pressure) in the feasible domain. This approach is applied to a simple network and a realistic large-scale network. Results show that prior nodal pressure information can significantly increase estimation accuracy and decrease the uncertainty, and the estimated nodal pressure can be confined to a feasible domain.

Different regulatory approaches to enhanced water protection in selected European jurisdictions

ABSTRACT This paper presents the results of the analysis of initiatives taken by selected European Union member states concerning enhanced water protection with respect to ownership and management of water resources and water distribution systems. Two of the countries studied have recently enacted their constitutional protection of water (Slovakia and Slovenia), one country is planning to reinforce the protection of water in its constitution (Czech Republic) and one state found the constitutional protection of water unnecessary (Finland). Whereas the reasons for (not) protecting water at the constitutional level vary widely, the common denominator is a strong support for protecting water as resource.

Computational Tools for Supporting the Operation and Management of Water Distribution Systems towards Digital Transformation

This paper presents a set of computational tools specially developed for supporting the operation and management of water distribution systems towards digital transformation of water services. These tools were developed in the scope of two R&D projects carried out in Portugal, DECIdE and WISDom, during 2018–2022. The DECIdE project focused on the development of tools for importing cadastral and operational data, as well as on the three operational tools for supporting the performance assessment: the first allows the calculation of different key performance indicators, both at a global and sectorial level, which is an annual requirement of the water regulator, and the other two allow the calculation of the water and the energy balances and a set of complementary indices. The WISDom project aimed at the implementation of applications that directly address specific water utility needs, namely, the flow rate data processing, the optimal location of pressure sensors, the identification of critical areas in the distribution network for pipe burst location, and the prioritization of pipes for rehabilitation. Implemented tools are useful to support water utilities in the daily operation and management of their systems, being a step forward towards digital transformation of the water sector.

Full-scale determination of pipe wall and bulk chlorine degradation coefficients for different pipe categories

Abstract Having good information about parameters that impact water quality can improve the management of water distribution systems in the short-term (optimising disinfection) and the long-term (planning rehabilitation). Full-scale data on the degradation of the residual disinfectant for various pipe characteristics are difficult to obtain but necessary. As the most common disinfectant is chlorine, this paper aims to determine the most important pipe and/or hydraulic system characteristics in the chlorine degradation coefficients. Such characteristics were identified based on statistical analyses that relate them with range values of bulk and pipe wall degradation coefficients estimated in full-scale conditions in a real distribution system. The results showed that among pipe characteristics, the period of installation impacts significantly kw and kt. Results of kw for three different materials confirmed that residual chlorine degradation at the pipe walls for grey-cast iron, which is older and metallic, is much higher than that for ductile cast iron and PVC pipes. In older pipes, up to 97% of residual chlorine can be degraded at the pipe walls, while the role of bulk reactions can reach about 35% in newer pipes. The obtained information can be integrated to identify pipes for rehabilitation/renewal and locations for booster rechlorination.

Graph neural network for integrated water network partitioning and dynamic district metered areas

Water distribution systems (WDSs) are used to transmit and distribute water resources in cities. Water distribution networks (WDNs) are partitioned into district metered areas (DMAs) by water network partitioning (WNP), which can be used for leak control, pollution monitoring, and pressure optimization in WDS management. In order to overcome the limitations of optimal search range and the decrease of recovery ability caused by two-step WNP and fixed DMAs in previous studies, this study developed a new method combining a graph neural network to realize integrated WNP and dynamic DMAs to optimize WDS management and respond to emergencies. The proposed method was tested in a practical case study; the results showed that good hydraulic performance of the WDN was maintained and that dynamic DMAs demonstrated excellent stability in emergency situations, which proves the effectiveness of the method in WNP.

Novel approach for burst detection in water distribution systems based on graph neural networks

Sustainable management of water resources is a key challenge for the well-being and security of current and future society worldwide. In this regard, water utilities have to ensure fresh water for all users in a demand scenario stressed by climate change along with the increase in the size of cities. Dealing with anomalies, such as leakages and pipe bursts, represents one of the major issues for efficient water distribution system (WDS) operation and management. To this end, it is crucial to count on suitable methods and technologies to provide a quick, reliable, and accurate detection of such anomalies and supply disruption events. Therefore, this work proposes a novel WDS management framework based on the development of graph convolutional neural networks (GCN) models for bursts detection in WDSs. These methods rely on a WDS graph representation for a set of pressure and flow rates measures. Such a graph is used to design two GCN-based models to identify bursts. In addition, two conventional multi-layer perceptron models are used as the benchmarks to compare the graph-based methodologies. Finally, the proposed methodology is tested on a water utility network, showing the high potential of graph convolutional networks for anomaly detection on WDSs.

Maintaining the long-term accuracy of water distribution models with data assimilation methods: A comparative study

The upgrading of water supply services is calling for more accurate and adaptive numerical models to give insight into actual water distribution systems (WDSs), which underlines the importance of carefully calibrating model parameters. Due to unavoidable uncertainties in the calibration process such as measurement errors, errors in model parameters assumed to be known, and local-optimum of calibration algorithms, calibrated parameters could still contain non-negligible latent errors, and the calibrated model may not able to maintain its long-term accuracy when operating conditions change. To solve this problem, there is growing interest in adopting data assimilation (DA) methods to utilize more comprehensive information in long-term measurements to reduce the impact of uncertainties and maintain the accuracy and stability of calibrated models. In this study, two traditional calibration methods and four DA methods were tested and compared in two WDSs with different structures, which aims to form a general understanding of the behavior and applicability of different methods. The calibration results show that DA methods perform better than traditional methods and are more robust to different types of uncertainties, which provide an effective way to maintain the long-term accuracy of WDS models to enable better management of WDSs. Ensemble-based DA methods such as Particle Filter (PF) and Inferential-Measurement Kalman Filter (IMKF) performed well in the real-life system. They avoid linear approximation and can better estimate the impact of uncertainties to assimilate accurate correction information of the parameters. Gradient-based DA methods such as Extended Kalman Filter (EKF) and Variational Bayesian Adaptive Kalman Filter (VBAKF) have lower computational demand, but they are found to be less robust when dealing with large system uncertainties and nonlinearities.

Unsupervised anomaly detection in hourly water demand data using an asymmetric encoder–decoder model

Water demand forecasting (WDF) is essential for the design and optimal management of water distribution systems (WDS). Historical water demand data contribute significantly to WDF. Yet the obtained water demand data contain anomalies on occasions due to failures in WDS or monitoring systems. The contaminated water demand data are invalid to describe the actual water demand, thus degrading the performance of WDF models. However, the importance of anomaly detection in water demand data is underestimated, or at least not explicitly described in many published papers. To fill the gap, we propose an unsupervised anomaly detection method based on an asymmetric encoder–decoder (asyED) model. Different from the symmetric structure of a traditional autoencoder where a signal is reproduced from itself, asyED is asymmetric where a signal is reproduced from the upstream and downstream information of the signal, while the signal itself does not participate in the reconstruction. In light of this feature, asyED is powerful in identifying anomalies. The proposed method is employed to detect anomalies in hourly water demand data which exhibit trend and seasonality. The results show the superiority of the proposed method over the other four commonly used anomaly detection methods: Z-score, isolation forest, local outlier factor, and seasonal hybrid ESD (Extreme Studentized Deviate test). • An anomaly detection method based on an asymmetric encoder-decoder model is proposed. • The method applies to hourly water demand data which exhibit trend and seasonality. • A cluster-based metric is proposed for model evaluation. • The metric considers the continuity mechanism of anomalies found in the data. • Measures to quantify the strengths of different components in the data are proposed.

Asynchronous sensor networks for Nodal water demand estimation in water distribution systems based on sensor grouping analysis

Real-time hydraulic models are important tools for the management of water distribution systems (WDS). In such systems, high frequency nodal water demands are required for real-time modeling. Due to the limitations of the sensors' technology and power supply, the sensors distributed in the WDS typically upload data at a low frequency. However, replacing all existing low frequency sensors with new high frequency sensors is not cost effective. To solve this problem, an asynchronous data uploading strategy is proposed, which uses current low frequency sensors to estimate nodal water demand at high frequency while maintaining model accuracy. Based on an innovative clustering algorithm, the method splits the information redundancy sensors into multiple groups. Sensors in different groups asynchronously upload data at different time points to estimate nodal water demand. Applications to a simple hypothetical WDS and a realistic WDS demonstrate that the developed approach can efficiently improve the data upload frequency of the sensor network, thus boosting the demand estimation frequency. The developed method is expected to reduce the cost of upgrading sensor networks and increase the efficiency of WDS modeling, thus facilitating the cleaner production and sustainable management of WDS.

Flexible decision-making framework for developing operation protocol for water distribution systems

Past water distribution systems (WDS) management studies derived operation protocols to maximize WDS reliability by using residual chlorine as the sole surrogate parameter for water quality reliability. Albeit the advancement in mechanistic modeling to examine the WDS water quality, emerging water quality parameters of concern are not yet involved in solving WDS management problems. This paper attempts to overcome this limitation by developing a flexible decision-making framework -integrating EPANET-C, a mechanistic modeling tool for WDS water quality, with Analytic Hierarchy Process (AHP), a multi-criteria decision-making method - to rank the possible water quality parameter-based operating alternatives (organic matter and residual chlorine levels at the source points) for WDS. The uncertainty analysis was incorporated into the mechanistic modeling using the Monte Carlo method to realize insufficient knowledge about the complex biological and physicochemical interactions inside WDS. Six cases, each ranking the alternatives diversely, were applied to reflect the expert judgment impressions on the AHP outcomes. The consistency of the proposed decision-making framework was verified by deriving the operation protocol for two test networks by making trade-offs between the multiple and conflicting microbiological, chemical, and organoleptic quality criteria. The disinfection by-products formation control and taste and odor problems control emerged as the most critical water quality criteria determining the WDS performance under the operating alternatives examined. Altogether, the obtained results suggested the practicality of adopting a flexible operation protocol to maintain the water quality benchmarks over various plausible WDS performance scenarios, ranging from worst to best.

A real-time and eco-layout platform for optimization of supply/costs for water distribution systems management

Abstract This research discusses developing a coupled system with both structural and operational aspects of the water distribution system. Operating view is provided through a real-time control scheduler (RTC), which satisfactorily attends to solve the dynamic control problem at every timestep via minimization of energy costs over the day and satisfying hydraulic reliability constraints through suggesting near-optimal pump schedules. Moreover, the network layout provides the structural view with a focus on inventing the most prosperous cost-effective topology. The modeling process was exerted by group-based machine learning techniques, a dynamic random search (DDS) algorithm and ultimately, the model performance was evaluated. In addition to providing stable hydraulic conditions, evaluating the coupled optimization platform (RTC-eco-layout) formulation on a typical day was adequate to beget an average of up to 23% daily energy savings as well as preserving the hydraulic feasibility properties in the range of up to 30% energy cost economies. The sensitivity analysis admitted that both operating and environmental variables contribute to the total uncertainty.

A framework for forecasting the hourly nodal water demand and improving the performance of real-time hydraulic models considering model uncertainty

Abstract The real-time hydraulic model (RTHM) is a key assistive tool in water distribution system (WDS) management, and its performance directly affects assisted decision-making. This study develops a framework to improve the timeliness and accuracy of RTHMs, which includes the following five steps: flow data processing, establishing nodal water demand (NWD) prediction models, node grouping, data assimilation (DA) and uncertainty analysis. Based on the actual network data, the performance of two data processing methods and three machine learning algorithms are, respectively, compared, and the best is selected for modeling. In the establishment of the hourly NWD prediction models, massive data, including flow measurement and data of all 26 input variables on climate, time and social influencing factors are used. It is found that the time features are the most important model input parameter. Application results of actual network prove that the flow data processing method, accurate NWD prediction, node grouping and Kalman filter-based DA method reduce the uncertainty in the RTHM and improve its timeliness and accuracy, so as to obtain the real-time state estimation of the WDS. Accurate NWD estimation (especially in the high-demand period) and combining RTHM with DA have a great influence on the uncertainty reduction in water pressure estimation, although uncertainty is weakened in the propagation process.