Performance Evaluation of WaterGEMS Software for Leakage Detection of Water Distribution System

Leakage in water distribution networks will cause waste of water and reduced pressure. Different leak detection methods are used in the networks among which the Meta-search algorithms have received much attention in the recent years. WaterGEMS commercial software uses genetic algorithm for optimal design and calibrate water distribution networks and detect leakage. In this paper, the WaterGEMS V8i performance in leakage detection using Darwin Calibrator tool was investigated in two hypothetical networks (Poulakis and Aniton). In the Poulakis network where only the node's pressure was put into the software as observational data, the location of leakage was determined at or in the vicinity of the exact location. However, in the Aniton network, where the input discharge was also introduced to the program as observational data, the location and the amount of the leakage were calculated more accurately. These results were similar to the leakage resulted in using the Ant colony algorithm.WaterGEMS is therefore evaluated as a good tool for engineers for estimating the location and amount of leakage in water networks.