Pressure Management Model for Urban Water Distribution Networks

A technique for leakage reduction is pressure management, which considers the direct relationship between leakage and pressure. To control the hydraulic pressure in a water distribution system, water levels in the storage tanks should be maintained as much as the variations in the water demand allows. The problem is bounded by minimum and maximum allowable pressure at the demand nodes. In this study, a Genetic Algorithm (GA) based optimization model is used to develop the optimal hourly water level variations in a storage tank in different seasons in order to minimize the leakage level. Resiliency and failure indices of the system have been considered as constraints in the optimization model to achieve the minimum required performance. In the proposed model, the results of a water distribution simulation model are used to train an Artificial Neural Network (ANN) model. Outputs of the ANN model as a hydraulic pressure function is then linked to a GA based optimization model to simulate hydraulic pressure and leakage at each node of the water distribution network based on the water level in the storage tank, water consumption and elevation of each node. The proposed model is applied for pressure management of a major pressure zone with an integrated storage facility in the northwest part of Tehran Metropolitan area. The results show that network leakage can be reduced more than 30% during a year when tank water level is optimized by the proposed model.