Data-driven control-oriented modelling for MPC-based control of urban drainage systems

TL;DR

This paper introduces a data-driven, control-oriented modeling approach for urban drainage systems, enhancing model accuracy and control performance within an MPC framework, demonstrated on a Madrid benchmark.

Contribution

It develops a novel methodology combining data, expert knowledge, and data-fitting for urban drainage system modeling, improving MPC control effectiveness.

Findings

High model accuracy achieved

Reduced discharge in control applications

Increased utilization of treatment facilities

Abstract

This article presents a data-driven, control-oriented modelling methodology for urban drainage systems (UDS). The proposed framework requires three main key components: input-output data from the element to be modelled, expert knowledge to define the model structure, and data-fitting techniques to obtain optimal parameters. The methodology is evaluated using a realistic benchmark from an UDS in Madrid, Spain. The results show high model accuracy and improved performance within a MPC scheme, reducing discharge and increasing treatment facilities utilization.