Abstract
Proper performance of water distribution networks (WDNs) plays a vital role in customer satisfaction. The aim of this study is to conduct a sensitivity analysis to evaluate the behavior of WDNs analyzed by a pressure-driven analysis (PDA) approach and the classification technique by using an appropriate artificial neural network, namely the Group Method of Data Handling (GMDH). For this purpose, this study is divided into four distinct steps. In the first and second steps, a real network has been analyzed by using a Pressure-Driven Analysis approach (PDA) to obtain the pressure, and α coefficient, the percentage of supplied flow. The analysis has been performed by using three different values of the design peak coefficient k*. In the third step, the Group Method of Data Handling (GMDH) has been applied and several binary models have been constructed. The analysis has been carried out by using input data, including the real topology of the network and the base demand necessary to satisfy requests of users in average conditions and by assuming that the demand in each single one-hour time step depends on a peak coefficient. Finally, the results obtained from the PDA hydraulic analysis and those obtained by using them in the GMDH algorithm have been compared and sensitivity analysis has been carried out. The innovation of the study is to demonstrate that the input parameters adopted in the design are correct. The analysis confirms that the GMDH algorithm gives proper results for this case study and the results are stable also when the value of each k*, characteristic of a different time hour step, varies in an admissible technical range. It was confirmed that the results obtained by using the PDA approach, analyzed by using a GMDH-type neural network, can provide higher performance sufficiency in the evaluation of WDNs.
Highlights
Concern regarding urban water distribution networks has led to increasing awareness and demand for evaluating WDNs to increase their performance and customer satisfaction [1]
The analysis of a network in different conditions has been used in the approach to calibrate hydraulics in both demand-driven analysis (DDA) and pressure-driven analysis (PDA)-based models
This study focuses on the real network application of the PDA approach to perform the network analysis and the Group Method of Data Handling (GMDH) algorithm to classify the network results
Summary
Concern regarding urban water distribution networks has led to increasing awareness and demand for evaluating WDNs to increase their performance and customer satisfaction [1]. Reviewing previous studies shows that urban water demand is more complex than irrigation, commercial, industrial, and energy demands [4]. Raúl Baños et al investigated the uncertainty of demand and the influence on the models in terms of resilience Indexes for Water Distribution. The capability of the system to provide the requested demand to all users has been investigated by Farmani et al, who included demand uncertainty in their approach [6]. The analysis of a network in different conditions has been used in the approach to calibrate hydraulics in both demand-driven analysis (DDA) and pressure-driven analysis (PDA)-based models. Tabesh et al use a genetic algorithm, analyzing different scenarios of lowest, normal, maximum, and fire consumption [7]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
