Online Hydraulic State Prediction for Water Distribution Systems

This paper describes and demonstrates a method for on-line hydraulic state prediction in urban water networks. The proposed method uses a Predictor-Corrector (PC) approach in which a statistical data-driven algorithm is applied to estimate future water demands, while near real-time field measurements are used to correct (i.e., calibrate) these predicted values on-line. The calibration problem is solved using a modified Least Squares (LS) fit method. The objective function is the minimization of the least-squares of the differences between predicted and measured hydraulic parameters (i.e., pressure and flow rates at several system locations), with the decision variables being the consumers' water demands. The a-priori estimation (i.e., prediction) of the values of the decision variables, which improves through experience, facilitates a better convergence of the calibration model and provides adequate information on the system's hydraulic state for real time optimization. The proposed methodology is demonstrated on a prototypical municipal water distribution system.