The Performance of Differential Evolution Algorithm for Leak Detection in Water Distribution Networks Considering The Uncertainty of Nodal Demands

Water supply networks are one of the most important urban infrastructures for supplying water. Considering that currently water wastage is a global concern and on the other hand the demand for water is increasing, this issue has made it necessary to manage the demand and modify the consumption pattern. One of the important components of non-revenue water is leakage in the water supply network, and leak detection is one of the necessary measures to reduce non-revenue water and manage consumption. In this research, an optimization formulation has been developed for the purpose of leak detection in water networks assuming the lack of information on the number of leaks and pressure measurement data, and the search problem has been solved with the differential evolution algorithm. The performance of the developed model has been investigated by defining different scenarios in terms of location, amount and number of leaks. First, the location scenarios were examined in terms of the number and amount of leaks, including one, ten, and twenty leaks at the same time, and then the developed model was implemented for location scenarios with an unknown number of leaks and the uncertainty of nodal needs. The results showed that the success of the model in the case of the certainty of the input data and the existence of a node is 100%, and by considering the hourly changes in the nodal demand and increasing the number of leaks up to ten and twenty leak nodes, the success rate of the model in finding the exact leak points is 95% and 94.5% has been obtained. In the scenarios where the number of leaks was considered unknown, the success of the model to find the number of leaks is 94%. The success of the model in the case of uncertainty of nodal requirements with the number of known leaks reaches 91% with the increase of leaks and 86% with the number of unknown leaks.