Sensor placement for classifier-based leak localization in water distribution networks using hybrid feature selection

This chapter presents a sensor placement method for the classifier-based approaches for leak localization in water distribution networks introduced in the previous chapter. The proposed approach formulates the sensor placement problem as a binary optimization problem. Because of the complexity of the resulting optimization problem, it is solved by means of Genetic Algorithms. In order to reduce the number of sensor configurations to test, a binary matrix that identifies pairs of sensors providing the same information is added as a constraint. The sensors are placed in an optimal way maximizing the accuracy of the leak localization. The proposed approach is first illustrated by means of the application to an academic example based on the Hanoi network. Then, a more realistic case study is proposed based on the Limassol district metered area.