A new method for identifying a leaking pipe within a pressurized water distribution system is presented. This novel approach utilizes transient modeling to analyze water networks. Urban water supply networks are important infrastructure that ensures the daily water consumption of urban residents and industrial sites. The aging and deterioration of drinking water mains is the cause of frequent burst pipes, thus making the detection and localization of these bursts a top priority for water distribution companies. Here we describe a novel method based on transient modeling of the water network and produces high-resolution pressure response under various scenarios. Analyzing this data allows the prediction of the leaking pipe. The transient pressure data is classified as leaking pipes or no leak clusters using the K-nearest neighbors (K-NN) algorithm. The transient model requires a massive computation effort to simulate the network’s performance. The classification model presented good performance with an overall accuracy of 0.9 for the basic scenarios. The lowest accuracy was obtained for interpolated scenarios the model had not been trained on; in this case, the accuracy was 0.52.

The optimal operation of water distribution systems (WDS) is a paramount objective for water utilities due to the substantial energy consumption associated with pumping. A major challenge in optimizing WDS operation is addressing uncertainties such as those related to consumer demands. Real‐time operation under uncertainty necessitates a dynamic approach that can utilize the newly observed information and adjust the operational policy accordingly. This study presents an adjustable robust optimization (ARO) approach to tackle this challenge. Unlike static optimization methods, ARO generates a decision rule policy that is dynamically adjusted as new data becomes available and the operational horizon evolves, thereby ensuring adaptability to changing conditions. Furthermore, the study includes a quantitative analysis of typical demand uncertainty that supports the formulation of the ARO model. The proposed method is evaluated through two case studies and compared with traditional folding horizon approaches. The results indicate that the ARO method is competitive with traditional methods in terms of objective value and surpasses them in terms of robustness. An additional advantage of the method is its offline operation capability which enables it to produce decision rules independent of real‐time programs. This feature facilitates various practical applications such as what‐if analyses, maintenance work planning, and preparation for other special events.

The operation of water distribution systems (WDS) is an energy-intensive process, which is subject to constraints such as consumer demands, water quality, and pressure domains. As such, tracing an operation policy in which constraints are met while energy costs are minimized, is a foremost objective for water utilities. Given the inherent uncertainties in WDS operation and the importance of supply continuity, it is essential to find an operational strategy that is robust against a wide range of circumstances. One promising approach for optimization under uncertainty is robust optimization (RO), which assures a robust (feasible) solution to realizations of the uncertain parameters, within predefined bounds. This study presents an RO-based method for optimizing pump scheduling under uncertainties of consumer demands and pumping costs. The method can capture various types of correlations between the uncertain parameters, thus better reflecting the uncertain nature of WDS operation. The developed methodology is demonstrated in two case studies with different levels of complexity. The impacts of uncertainty levels and correlation coefficients are analyzed to demonstrate their implications on operation policy. The results show the advantages of using RO with tradeoffs between costs and constraints satisfaction.

Recent developments in control theory, coupled with the growing availability of real‐time data, have paved the way for improved data‐driven control methodologies. This study explores the application of the Data‐Enabled Predictive Control (DeePC) algorithm to optimize the operation of water distribution systems (WDS). WDS are characterized by inherent uncertainties and complex nonlinear dynamics. Hence, classic control strategies involving physical model‐based or state‐space methods are often difficult to implement and scale. The DeePC method suggests a paradigm shift by utilizing a data‐driven approach. The technique employs a finite set of input‐output samples (control settings and measured data) to learn an unknown system's behavior and derive optimal policies, effectively bypassing the need for an explicit mathematical model of the system. In this study, DeePC is applied to two WDS control applications of pressure management and chlorine disinfection scheduling, demonstrating superior performance compared to standard control strategies.