Management Of Water Distribution Systems Research Articles

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.

Per capita water consumption for benchmarked South African service levels derived by means of explicit reasoning

Per capita water use is commonly employed in single-parameter models to estimate water demand, especially in regions where model input parameters are limited. Research has confirmed that the serviced population and household size positively correlate with water consumption, but the per capita consumption of household members decreases with increased household size. A central issue driving this study was the lack of an up-to-date per capita household water use guideline in the South African context. This study followed a process of explicit reasoning and inference, informed by an extensive knowledge review, stakeholder input and interrogation of relevant data, to develop a novel per capita water use estimation tool. Five main parameters were included, namely: (i) level of water service provided, (ii) usage scenario, (iii) household size (people per household), (iv) geographic region, and (v) regional property value. A Microsoft Excel–based tool was developed and is supplied online as supplementary material with this publication. The litres per capita per day tool (LCD-tool) allows for robust per capita water use estimates, as a function of the above five input parameters. The Microsoft Excel LCD-tool provides benchmarks for different South African conditions, described by context-specific service levels. The planning and management of water supply and distribution systems could benefit from the findings of this study.

Flexible and deterministic household water saving under water demand uncertainty: existing water distribution system and sanitary sewer perspectives

Abstract An integrated method that evaluates conflicting hydraulic performances of water distribution systems (WDSs) and sanitary sewers (SSs) considering water-saving schemes (WSSs) under fixed (deterministic) or uncertain water demands was formulated. WSSs considered include household water-saving fixtures and appliances whose water flows impact water distribution system (WDS) and sanitary sewer (SS) hydraulic performances in different ways. In the proposed flexible approach, a multi-objective optimisation problem was formulated and solved considering trade-offs of three objectives: (1) maximisation of the average cost savings (2) maximisation of the average WDS resilience index and (3) minimisation of the average SS self-cleansing velocity deficit factor. The decision variables include water-saving fixture and appliance capacities that are applied in a deterministic or flexible manner at a household level. The constraints include WDS and SS hydraulic requirements together with decision bounds of the available water-saving scheme capacities. The non-dominated sorting genetic algorithm was used to obtain trade-off solutions. This method was demonstrated in the corresponding WDS and SS network subsystems of Tsholofelo extension in Gaborone, Botswana. The results indicate that WSSs lead to visibly conflicting WDS and SS hydraulic performances. Moreover, considering the uncertainty inherent in water demand and the corresponding planning and management of WDSs and SSs provides more sustainable solutions as demand uncertainties unveil.

Comparison of Imputation Methods for End-User Demands in Water Distribution Systems

AbstractThis study examines the impact of advanced metering infrastructure (AMI) end-user demand metering failure on water distribution system (WDS) operation and management. To address this issue,...

Evaluasi dan Arahan Peningkatan Pelayanan Air Bersih di Kota Makassar

Clean water services are still a problem faced by the Makassar City government, South Sulawesi. The high demand for clean water services is currently not being handled properly. The aim of this research is to determine the factors that affect clean water services and the problems. This research was conducted from April 2019 to January 2020 (10 months). This research used primary and secondary data. The analysis used in this research is descriptive analysis with qualitative and quantitative approaches and spatial analysis through mapping using the ArcMap application. The results showed that the factors affecting clean water services in Makassar City are clean water sources, production capacity, location, number of people served, climate, water loss (leakage), water treatment management, and financing. Problems experienced by the community in clean water services in Makassar City are leaks, not running water, checking bills, problematic meters, dirty and smelly water, broken pipes, problematic payments and others (new installation and moving meters). To fulfill the need for clean water in Makassar City, can be added with additional water sources which are processed and distributed to the community, by using water from rivers around Makassar City and utilizing rain water harvesting or seawater desalination. In addition, it is necessary to improve the clean water distribution system and water treatment management from the source to the distribution of water to the community to reduce the level of water loss.

Optimization Methodology for Estimating Pump Curves Using SCADA Data

Water distribution systems (WDSs) deliver water from sources to consumers. These systems are made of hydraulic elements such as reservoirs, tanks, pipes, valves, and pumps. A pump is characterized by curves which define the relationship of the pump’s head gain and efficiency with its flow. For a new pump, the curves are provided by the manufacturer. However, due to its operating history, the performance of a pump deteriorates, and its curves decline at an estimated rate of about 1% per year. Pump curves are key elements for planning and management of WDSs and for monitoring system efficiency, to determine when a pump should be rehabilitated or replaced. In practice, determining pump curves is done by field tests, which are conducted every few years. This leaves the pump’s performance unmonitored for long time periods. Moreover, these tests often cover only a small range of the curves. This study demonstrates that in the era of IoT and big data, the data collected by Supervisory Control And Data Acquisition (SCADA) systems can be used to continuously monitor pumps’ performance and derive updated pump characteristic curves. We present and demonstrate a practical methodology to estimate fixed and variable speed pump curves in pumping stations. The proposed method can estimate individual pump curves even when the measurements are given only for the pumping station as a whole (i.e., total flow, pumping station head gain). The methodology is demonstrated in a real-world case study of a pumping station in southern Israel.

Designing of water distribution system

Water distribution system (WDS) aims to distribute water from reservoirs or aqueducts to the end-users. This system is part of the water supply network that carries potable water from a central treatment plant or wells to water consumers in order to deliver water sufficiently to meet residential, commercial, industrial, and firefighting requirements. Modern systems aim to solve water distribution systems management problems, such as the lowest cost, and most efficient design by using linear/nonlinear optimization schemes, which are limited by the system size, the number of constraints, and the number of loading conditions. After a literature review for the articles that dealt with this topic, designing two parts of the water distribution system is discussed as a case study in Erbil. Pumps and storage tanks, while optimizing the water distribution system by minimizing the project cost through minimizing the volume of the elevated tank according to the pump working hours.

Minimizing Pumping Energy Cost in Real-Time Operations of Water Distribution Systems Using Economic Model Predictive Control

Optimizing pump operations is a challenging task for real-time management of water distribution systems (WDSs). With suitable pump scheduling, pumping costs can be significantly reduced. In this research, a novel economic model predictive control (EMPC) framework for real-time management of WDSs is proposed. Optimal pump operations are selected based on predicted system behavior over a receding time horizon with the aim to minimize the total pumping energy cost. Time-varying electricity tariffs are considered while all the required water demands are satisfied. The novelty of this framework is to choose the number of pumps to operate in each pump station as decision variables in order to optimize the total pumping energy costs. By using integer programming, the proposed EMPC is applied to a benchmark case study, the Richmond Pruned network. The simulation with an EPANET hydraulic simulator is implemented. Moreover, a comparison of the results obtained using the proposed EMPC with those obtained using trigger-level control demonstrates significant economic benefits of the proposed EMPC.

Research on Hydraulic Safety Assessment of Water Distribution Systems

There are two key issues in the safety assessment of the water distribution system (WDS). One is how to evaluate the safety levels of water supply for customers, while the other is how to describe the importance of a pipe for the global or local WDS. The water demand guarantee rate (DGR) and the water demand failure rate (DFR) are proposed. The mathematical expectations of the DGR and DFR describe the average customer’s water safety levels for the first issue. Moreover, the unit influence of pipe failure (UIPF) is put forward for the second issue. It describes the importance of the pipe for the global or local system. Several cases show how to calculate the above values with the pressure-driven model. It is also shown how to find key pipelines in the WDS. The results show that the method can provide an effective reference for real-life WDS management.

Triple Top Line–Based Sustainability Measure for Water Distribution Systems

AbstractTo address the rapidly growing need for asset management of aging water distribution systems (WDS), this study introduces the adaptation of the triple top line (TTL) as a tool for WDS susta...

Hybrid Model for Short-Term Water Demand Forecasting Based on Error Correction Using Chaotic Time Series

Short-term water demand forecasting plays an important role in smart management and real-time simulation of water distribution systems (WDSs). This paper proposes a hybrid model for the short-term forecasting in the horizon of one day with 15 min time steps, which improves the forecasting accuracy by adding an error correction module to the initial forecasting model. The initial forecasting model is firstly established based on the least square support vector machine (LSSVM), the errors time series obtained by comparing the observed values and the initial forecasted values is next transformed into chaotic time series, and then the error correction model is established by the LSSVM method to forecast errors at the next time step. The hybrid model is tested on three real-world district metering areas (DMAs) in Beijing, China, with different demand patterns. The results show that, with the help of the error correction module, the hybrid model reduced the mean absolute percentage error (MAPE) of forecasted demand from (5.64%, 4.06%, 5.84%) to (4.84%, 3.15%, 3.47%) for the three DMAs, compared with using LSSVM without error correction. Therefore, the proposed hybrid model provides a better solution for short-term water demand forecasting on the tested cases.

Using criticality categories to evaluate water distribution networks and improve maintenance management

Deficient maintenance management of water distribution systems is an issue in many countries around the world. In northeast Brazil, losses of water during its distribution has reached 42.7 %. Maintenance planning is essential to improve efficiency in a water distribution system. Therefore, a framework was proposed that combines Strategic Options Development and Analysis (SODA) with the ELECTRE TRI-nC method to sort areas into criticality categories in order to determine priorities for monitoring a maintenance service. To provide a global characterization, three categories are recognized: “Not critical,” “Moderately critical,” and “Highly critical.” The proposed framework is applied in a real case study of a municipality located in the northeast of Brazil (Itamaracá/Pernambuco). This framework provides (i) managerial priorities to support maintenance decisions that improve the action planning of the water company, (ii) formal and structured knowledge about the water distribution system, and (iii) benefits to society, such as improving the quality of service, reducing costs, and preserving water resources. Our study demonstrates that actions such as developing awareness -raising campaigns about the rational use of water, installing pressure and flow control valves and establishing sectorization in the network system are essential in order to improve how maintenance is managed.

Building and exploiting a Digital Twin for the management of drinking water distribution networks

ABSTRACT Digital Twins (DTs) are starting to be exploited to improve the management of water distribution systems (WDSs) and, in the future, they will be crucial for decision making. In this paper, the authors propose several requirements that a DT of a water distribution system should accomplish. Developing a DT is a challenge, and a continuous process of adjustments and learning is required. Due to the advantages of having a DT of the WDS always available, during the last years a strategy to build and maintain a DT of the water distribution network of Valencia (Spain) and its Metropolitan Area (1.6 million inhabitants) was developed. This is one of the first DTs built of a water utility, being currently in operation. The great benefits of their use in the daily operation of the system ensure that they will begin to be usual in the most advanced smart cities.

A Short-Term Planning Framework for the Operation of Tanker-Based Water Distribution Systems in Urban Areas

Tanker-based distribution systems have been prevalent in developing countries to supply clean and pure water in different regions. To efficiently operate such tanker service systems, a large fleet of tanker trucks are required to transport water among several water sources, water treatment plants and consumers spanning across the regions. This requires tighter coordination between water suppliers, treatment plant operations, and user groups to use available water resources in a sustainable manner, along with the assurance of water quality and timely delivery. This paper proposes a novel formulation to assist decision-making for optimizing tanker-based water distribution systems and treatment operations, with an overall objective of minimizing the total operating cost such that all of the constraints related to the water demand, supply operations, and environmental and social aspects are honored while supplying water to a maximum number of users. The problem is formulated and solved as a mixed integer linear programming (MILP) optimization framework and captures all of the nuances related to (i) water availability limitations and quality constraints from different sources, (ii) maintaining water quality as it transports via tankers, (iii) water demands for various end-use purposes, and (iv) transportation across a water supply chain. The proposed novel framework is applied to a realistic urban model to find the optimal tanker delivery schedule, ensuring appropriate treatment and timely delivery of water. The results of the case study conducted on a representative-scale problem also elucidate several aspects of treatment plant operation and consumer demand fulfillment for the efficient planning and management of tanker-based water distribution systems.

Applying the mathematical optimization model in water distribution management

This paper aims to analyse the concept of water distribution system management and the modalities of including the optimization tools for increasing the process efficiency. Water distribution systems are often unable to respond quickly and efficiently to consumers demands. Water is a non-renewable resource and should therefore be treated with special interest. Sustainable development and optimization are the steps to take. A mathematical optimization model is presented in the second part of the paper with explanations regarding the steps followed. The result demonstrates the efficiency, speed and accessibility of using graphical-analytical optimization methods in the field of water distribution system.

Zero-net energy management for the monitoring and control of dynamically-partitioned smart water systems

Abstract The optimal and sustainable management of water distribution systems still represent an arduous task. In many instances, especially in aging water net-works, pressure management is imperative for reducing breakages and leakages. Therefore, optimal District Metered Areas represent an effective solution to decreasing the overall energy input without performance compromise. Within this context, this paper proposes a novel adaptive management framework for water distribution systems by reconfiguring the original network layout into (dynamic) district metered areas. It utilises a multiscale clustering algorithm to schedule district aggregation/desegregation, whilst delivering energy and supply management goals. The resulting framework was tested in a water utility network for the simultaneously production of energy during the day (by means of the installation of micro-hydropower systems) and for the reduction of water leakage during the night. From computational viewpoint, this was found to significantly reduce the time and complexity during the clustering and the dividing phase. In addition, in this case, a recovered energy potential of 19 MWh per year and leakage reduction of up to 16% was found. The addition of pump-as-turbines was also found to reduce investment and maintenance costs, giving improved reliability to the monitoring stations. The financial analyses to define the optimal period in which to invest also showed the economic feasibility of the proposed solution, which assures, in the analysed case study, a positive annual net income in just five years. This study demonstrates that the combined optimisation, energy recovery and creation of optimized multiple-task district stations lead to an efficient, resilient, sustainable, and low-cost management strategy for water distribution networks.