|
Abstract
|
There is a growing concern over the need for the renovation of water distribution networks (WDNs) in Iran. According to statistics, more than 30% of pipes in WDNs are more than 25 years old. There is no effective method for identifying the priority pipes to be replaced or repaired. The main scope of this research is to present a new method for renovation planning of WDNs. A multi-objective ACO metamodel is developed by the combination of WDN simulator model (EPANET), an artificial neural network and ant colony optimization algorithm within MATLAB. Comparison of the results in the sample network showed that the design and renovation planning of the network during its lifecycle can create lower costs and higher reliability. In the real WDN, by applying the renovation planning, the operational costs reduced and the indices improved relatively. For example, the MaxPO index decreased from 11.8 to 5.8%.
|