Data-Enabled Predictive Control for Optimal Pressure Management

Recent developments in control theory coupled with the growing availability of real-time data have paved the way for improved data-driven control methodologies. This study explores the application of a data-enabled predictive control (DeePC) algorithm to optimize the operation of water distribution systems (WDS). WDSs are characterized by inherent uncertainties and complex nonlinear dynamics. Hence, classic control strategies that involve physical model-based methods are often hard to implement and infeasible to scale. The DeePC method suggests a paradigm shift by utilizing a data-driven approach. This method employs real-time data to dynamically learn an unknown system’s behavior. It utilizes a finite set of input–output samples (control settings, and measured data) to derive optimal policies, effectively bypassing the need for an explicit mathematical model of the system. In this study, DeePC is applied to a pressure management case study and demonstrates superior performance compared to standard control strategies.