Water Distribution Systems Research Articles

Robust adaptive optimization for sustainable water demand prediction in water distribution systems

The advancement of the Internet of Things has positioned intelligent water demand forecasting as a critical component in the quest for sustainable water resource management. Despite the potential benefits, the inherent non-stationarity of water consumption data poses significant hurdles to the predictive accuracy of forecasting models. This study introduces a novel approach, the Robust Adaptive Optimization Decomposition (RAOD) strategy, which integrates a deep neural network to address these challenges. The RAOD strategy leverages the Complete Ensemble Empirical Mode Decomposition (CEEMD) to preprocess the water demand series, mitigating the effects of non-stationarity and non-linearity. To further enhance the model’s robustness, an innovative optimization algorithm is incorporated within the CEEMD process to minimize the variance in multi-scale arrangement entropy among the decomposed components, thereby improving the model’s generalization capabilities. The predictive power of the proposed model is harnessed through the construction of deep neural networks that utilize the decomposed data to forecast minutely water demand. To validate the effectiveness of the RAOD strategy, real-world datasets from four distinct geographical regions are employed for multi-step ahead predictions. The experimental outcomes demonstrate that the RAOD model outperforms existing models across all considered metrics, highlighting its suitability for accurate and reliable water demand forecasting in the context of sustainable energy management.

Toward Identifying Cyber Dependencies in Water Distribution Systems Using Causal AI

Toward Identifying Cyber Dependencies in Water Distribution Systems Using Causal AI

Application of Interval Type-2 Fuzzy Linear Programming to Chlorine Injection in a Water Distribution System

Application of Interval Type-2 Fuzzy Linear Programming to Chlorine Injection in a Water Distribution System

Enhancing the accuracy and reliability of non-online metered demand allocation in water distribution systems through dynamic spatiotemporal population distribution

Enhancing the accuracy and reliability of non-online metered demand allocation in water distribution systems through dynamic spatiotemporal population distribution

A Hybrid Model Coupling Data and Hydraulic Transient Laws for Water Distribution Systems

AbstractThe physics‐informed neural network (PINN) method has been applied to solve water hammer equations in pipeline systems due to its ability of seamlessly integrate measurement data with conservation laws, offering advantages over traditional numerical method. However, existing PINN approaches require multiple neural networks to construct composite models for complex water distribution systems (WDS). This situation treats nodal information as boundary condition or labeled data during training, leading to a weaker robustness and a high demand for data. To address these issues, a hybrid water hammer model based on eXtended Physics‐Informed Neural Networks for WDS (WDS‐XPINN) is developed in this study. Unlike the standard PINN, WDS‐XPINN incorporates the nodal mechanistic model directly into the loss function, enabling to synchronously train a unified neural network jointly through sparse augmented measurement data for pipeline system. Additionally, an adaptive weights method is introduced to improve model robustness by balancing the contributions of flowrates and pressures. The proposed WDS‐XPINN is evaluated in two case studies: a series pipeline system with different operational events and noise perturbation, as well as a topological structure with looped and branched pipe. According to the simulation results and uncertainty analysis, the WDS‐XPINN model demonstrates its excellent capacity of modeling fluid transient accurately in pipeline system, even without exact operational conditions or true pipe parameters.

Algal organic matter triggers re-assembly of bacterial community in plumbing system

Algal bloom outbreaks in upstream drinking water reservoirs inevitably lead to algal organic matter (AOM) pollution in downstream drinking water plants and distribution systems. However, the responses of indoor piped drinking water quality and microbial community to AOM remain to be well studied. In this study, we investigated the effects of low and high concentrations of Chlorella organic matters on pipe-based drinking water. We found that AOM introduced nitrogen and phosphorus contamination into drinking water and promoted massive regeneration of bacteria during stagnation, along with increased bacterial metabolic activity. Compared to the Control group, the utilization capacity of alcohols, acids, esters, and amino acids increased under the influence of AOM. In addition, AOM intrusion reduced the bacterial community diversity in drinking water. The bacterial communities became more saturated, interspecific relationships became more complex, and interspecific competition increased. Bacteria with the ability to denitrification, such as Pseudomonas putida, Sphingobium amiense, Delftia tsuruhatensis, and Acidovorax temperans, were the most abundant. Residual chlorine, ammonium, nitrite, and iron had notable effects on the bacterial community under the influence of AOM. The results help elucidate the response mechanism of microbial community to AOM contamination in indoor drinking water pipes and provide a scientific basis for drinking water safety risk management.

Maximizing efficiency and performance of water distribution systems through the implementation of optimization algorithms: A comprehensive analysis of valve and chlorine booster placement and management

Maximizing efficiency and performance of water distribution systems through the implementation of optimization algorithms: A comprehensive analysis of valve and chlorine booster placement and management

N-acyl-homoserine-lactones as a critical factor for biofilm formation during the initial adhesion stage in drinking water distribution systems.

The N-acyl-homoserine-lactone (AHLs)-mediated quorum sensing (QS) system is crucial for the coordination of microbial behaviors within communities. However, the levels of AHLs in biofilms in drinking water distribution systems (DWDSs) and their impact on biofilm formation remain poorly understood. Herein, we simulated DWDSs via biofilm reactors to explore the presence and influence of AHLs during the initial stages of biofilm formation on pipe walls. Glass, polypropylene random copolymer (PP-R) and stainless steel (SS) were used as the coupon materials and the three parallel experimental groups were set up and named accordingly. The glass material is considered to form biofilms only minimally and is therefore used as a negative control. By day 30, the concentration of AHLs in biofilm phase in both PP-R group and SS group reached 1200-1800ng/L. The predominant AHLs were C6-HSL, C8-HSL, and C10-HSL, with a significant positive correlation between AHLs and biofilm biomass. Metagenomic analysis revealed that microbes exhibiting significant differences among the three groups all demonstrated notable correlations with AHLs. Subsequent analysis of QS genes revealed that the genes associated with AHLs biosynthesis and QS receptors were more abundant in the PP-R and SS groups with biofilm formation. Additionally, we analyzed the abundance of genes related to cell motility, transmembrane transport, tricarboxylic acid cycle, and genetic information synthesis. The co-occurrence network indicates that these processes exhibit a strong correlation with QS genes. This study demonstrates the pivotal role of AHLs in microbial communication during the initial stages of biofilm formation in DWDSs and indicates that the regulatory pathways and mechanisms of AHLs may vary under different environmental conditions.

Machine learning for smart water distribution systems: exploring applications, challenges and future perspectives

The advancements of the Internet of Things and Low-Power Wide-Area Network technology will accelerate in the next future the adoption of smart meters in water distribution systems, enabling the collection of a huge amount of fine-grained data. How to turn massive smart meter data into actionable knowledge will be the key point to limit water wastage and promote efficient and sustainable distribution. Although the collection of data worldwide is currently limited, the potential future impact of exploiting data-driven and machine learning methods is increasingly recognized in research and industry, as shown by many scientific works published in recent years. In particular, the interest in deep learning for smart water distribution systems is increasing, motivated by the ability to learn intricate patterns from big data. This work aims to provide an overview of the current research and identify challenges for future directions by conducting an application-oriented survey. Specifically, by analysing data characteristics and operational targets, we propose a new taxonomy that helps structure properly the macro-areas of water management into infrastructure analysis, demand analysis and water quality monitoring. Existing methods are discussed for each application under these three stages. In addition, we also discuss potential research directions, such as federated learning, incremental learning, probabilistic modeling and explainability and address broad issues like data availability and implications for privacy.

Exploring the co-occurrence of microplastics, DOM and DBPs inside PVC pipes undergoing chlorination by correlation analysis and unsupervised learning.

Drinking water distribution systems face a multifaceted emerging concern, including in situ microplastic (MP) generation, chemical leaching from plastic pipes, and the formation of disinfection by-products (DBPs). This study investigated the co-release of MPs and chemical leachates from polyvinyl chloride (PVC) pipes exposed to different chlorine concentrations on a lab scale, as well as the subsequent formation of DBP. Results highlighted significant evidence of PVC-derived dissolved organic matter (PVC-DOM) and microplastic (PVC-MP) leaching at higher chlorine concentrations. However, at chlorine residuals of 1ppm, natural organic matter (NOM) retained its importance, with minimal release of PVC-DOM and PVC-MP from plastic pipes. Correlation analysis highlights the critical role of DOM, including both NOM and PVC-DOM, as a key intermediary between MPs and DBPs. This is evidenced by the strongest observed correlations within the DOM group and its significant associations with both MPs and DBPs. Conversely, the limited direct connections between MPs and DBPs further underscore the importance of DOM as the key link between these two targets. Using unsupervised learning techniques, including clustering and dimensionality reduction, further elucidated the influence of DOM in controlling the data patterns, enabling robust interpretation of complex datasets, and providing valuable insights. This study contributes to advancing understanding of the co-occurrence and behaviors of MP, DOM, and DBP within drinking water distribution systems, as well as propelling the associated risk in this intricate scenario.

Securing water distribution systems with hybrid lightweight attribute-based security scheme

Securing water distribution systems with hybrid lightweight attribute-based security scheme

Study on short-term mechanical properties of multi-reinforced steel-plastic composite pipe under internal pressure

A multiple-reinforced steel-plastic composite pipe (MRSPCP) is a new type of composite pipe developed in China recent years. The MRSPCP is composed of high-density polyethylene (HDPE) matrix, steel-wire mesh, and steel strip. It is an improved version of the traditional structural wall pipe, and it is able to carry both external and internal pressures. Nowadays, it has been employed in many projects that require large diameter and high flow media transportation, such as water distribution systems, drainage systems, agricultural irrigation systems. As the MRSPCP is newly developed, its mechanical properties and failure mechanism are not clear, and its design method lacks theoretical basis, so this paper carries out the experimental, theoretical and simulated research to investigate the short-term mechanical properties of the MRSPCP. Firstly, uniaxial tensile tests are carried out to acquire the mechanical properties of the constituents. As the steel wire is curly and it is hard to get the stress-strain relationship directly, an inverse identification method was applied to determine the mechanical parameters of a bilinear model representing the steel-wire mechanical behavior. Moreover, short-term burst tests of the MRSPCP are carried out to assess its mechanical performance and provide data for the verification of the theoretical and simulated research. Secondly, a theoretical model is established to calculate the failure pressure by constructing force equilibrium relationship along the axial and hoop directions of the MRSPCP respectively, based on elastic mechanics. In the end, a finite element model of MRSPCP is established, considering the nonlinear mechanical property of the materials. Both the theoretical and the simulated results agrees well with the burst test result, with the relative error of only −13.18% and −4.41% respectively. As the finite element model not only provides more accurate result, but also it can demonstrate contour plots of different constituents inside the MRSPCP, the model is used to study the effects of the pipe thickness, composite strip winding angle and steel-wire diameter on the mechanical properties of MRSPCP. This study might be a guide for the design and safe application of the MRSPCP and similar composite pipes.

Optimizing Reservoirs to Provide Water in Times of Crisis, With Emphasis on the Reuse of Treated Wastewater in Different Uses

Background: Natural disasters, such as earthquakes, can disrupt water distribution systems, leading to prolonged water shortages and associated crises. Tehran, with its high seismic risk, necessitates robust emergency water management solutions to ensure adequate potable and non-potable water supply during critical conditions. Methods: Using GIS and WaterGEMS software, we evaluated the design and placement of emergency water reservoirs in ASP Town, Shahriar. Hydraulic modeling was conducted to optimize the piping, pressure, and flow dynamics for potable water supply under emergency conditions. Additionally, non-potable water reservoirs utilizing treated wastewater were designed for irrigation and fire suppression, incorporating solar-powered pumping systems to ensure energy efficiency. Results: A 50 m3 cylindrical steel emergency tank, connected to the urban water network, was proposed to provide 3 L of potable water per person for three days in a crisis. The system includes solar panels, a 250-W pump, and a hydraulic shut-off valve to maintain water quality and availability. For non-potable uses, a wastewater reservoir with a variable-speed pumping station supports irrigation and supplies 12 fire hydrants, meeting pressure and flow requirements during emergencies. Conclusion: This study highlights the importance of integrated water management strategies, including solar-powered systems and treated wastewater reuse, to improve resilience against natural disasters. The proposed designs ensure sustainable water supply and effective crisis management for drinking and non-potable applications in high-risk urban areas.

Predicting few disinfection byproducts in the water distribution systems using machine learning models.

Concerns regarding disinfection byproducts (DBPs) in drinking water persist, with measurements in water treatment plants (WTPs) being relatively easier than those in water distribution systems (WDSs) due to accessibility challenges, especially during adverse weather conditions. Machine learning (ML) models offer improved predictions of DBPs in WDSs. This study developed multiple ML models to predict Trihalomethanes (THMs), Haloacetic Acids (HAAs), Dichloroacetonitrile (DCAN), and N-nitrosodimethylamine (NDMA) in WDSs using data collected over 13years (2008-2020) from 113 water supply systems (WSS) in Ontario. Data were collected tri-monthly (four times/year) following Ontario's regulatory requirements. Four common ML models-linear regressor (LR), random forest regressor (RFR), support vector regressor (SVR), and artificial neural networks with multiple folds cross-validation (ANN-MV) and single fold validation (ANN-SV)-were trained and tested using different datasets. R2 values for training datasets of THMs, HAAs, DCAN, and NDMA models ranged from 0.533 to 0.976, 0.560 to 0.980, 0.602 to 0.993, and 0.449 to 0.858, respectively. For testing datasets, R2 ranged from 0.517 to 0.939, 0.437 to 0.945, 0.565 to 0.973, and 0.517 to 0.718, respectively. Among THMs, HAAs, and DCAN, ANN-SV models were identified as the best, followed by the RFR model, whereas for NDMA, SVR was the superior model, followed by the LR model. Some models reliably predicted DBPs, suggesting they could replace costly sampling and experimental analysis for DBPs in the WDSs, thereby enhancing DBPs control in WDSs and reducing human exposure and associated risks.

Resilient isolation valve system design considering water shortage equity of water distribution system

The water distribution system (WDS) plays a crucial role in sustaining our society, serving as a vital lifeline. However, the performance of WDS is often compromised by various disturbances. To address this challenge and prevent functionality losses, isolation valves are strategically installed within the WDS. This study introduces a novel approach to isolation valve system (IVS) design, aiming to maximize equity during segment isolation. The proposed method utilizes an objective function centered on equity maximization. To achieve this, the study extends the conventional Gini coefficient by incorporating water demand ratio (reliability) instead of income. This adaptation results in the creation of the Water Lorenz Curve and Water Gini coefficient, which serve as essential metrics for assessing equity in the context of water distribution. An optimization model based on the genetic algorithm (GA) is developed, leveraging the newly introduced metrics. To evaluate the effectiveness of the proposed design approach, a comparison is drawn with the traditional reliability-based design approach. The study applies both models to five benchmark networks, providing insights into their respective performances. The application of these models to the benchmark networks highlights that, while the proposed approach may involve trade-offs in traditional reliability metrics, it excels in various performance indicators. This suggests the potential for a shift from reliability-based designs to equity-based designs without imposing significant cost burdens. Key performance metrics, including reliability, system robustness, resilience, hydraulic geodesic index, and valve installation cost, are employed to comprehensively compare the outcomes of the two design approaches.

Assessing impacts of climate crisis on water distribution systems though service inefficiency indicator

Assessing impacts of climate crisis on water distribution systems though service inefficiency indicator

Assessing Air-Pocket Pressure Peaks During Water Filling Operations Using Dimensionless Equations

Air pockets can become trapped at high points in pipelines with irregular profiles, particularly during service interruptions. The resulting issues, primarily caused by peak pressures generated during pipeline filling, are a well-documented topic in the literature. However, it is surprising that this subject has not received comprehensive attention. Using a model developed by the authors, this paper identifies the key parameters that define the phenomenon, presenting equations in a dimensionless format. The main advantage of this study lies in the ability to easily compute pressure surges without the need to solve a complex system of differential and algebraic equations. Numerous cases of filling operations were analysed to obtain dimensionless charts that can be used by water utilities to compute pressure surges during filling operations. Additionally, it provides charts that facilitate the rapid and reasonably accurate estimation of peak pressures. Depending on their transient characteristics, pressure peaks are either slow or fast, with separate charts provided for each type. A practical application involving a water pipeline with an irregular profile demonstrates the model’s effectiveness, showing strong agreement between calculated and chart-predicted (proposed methodology) values. This research provides water utilities with the ability to select the appropriate pipe’s resistance class required for water distribution systems by calculating the pressure peak value that may occur during filling procedures.

Determination of Weights and Priority Ranking of Leakage Management Components in Water Distribution Systems Using Analytical Hierarchy Process, Analytical Network Process and TOPSIS Methods

Determination of Weights and Priority Ranking of Leakage Management Components in Water Distribution Systems Using Analytical Hierarchy Process, Analytical Network Process and TOPSIS Methods

ANFIS method to enhance FMEA water operation model of Indonesia drinking water distribution system

Many problems are found in water treatment and distribution in water operations. Those problems range from low to critical risk. All critical risks must be addressed immediately. The Failure Mode and Effects Analysis (FMEA) prioritizes problems based on Occurrence, Severity, and Detection values to identify critical risks. However, this method is also having problems. With the same risk priority number (RPN) calculation, FMEA would be a ranking problem with the same RPN value; hence, we have a priority problem that is not critical but based on the highest value. To solve this problem, we propose additional methods, such as the ANFIS, to give weight based on risk level classification. From the results of data processing carried out by the ANFIS method, it is proven that it can perform re-ranking, for example, in the L2, R5, S8, and U3 code, which has an FMEA RPN value of 12. However, in FMEA-ANFIS, the RPN value becomes L2 2.05, R5 1.52, S8 1.32, and U3 2.52. Furthermore, with these results, it can be concluded that the ANFIS method can enhance the FMEA model in water operations.

Penalized spatial-temporal sensor fusion for detecting and localizing bursts in water distribution systems

Penalized spatial-temporal sensor fusion for detecting and localizing bursts in water distribution systems