Learning-Based Predictive Control with Gaussian Processes: An Application to Urban Drainage Networks

Krisztian Mark Balla*, Deividas Eringis, Mohamad Al Ahdab, Jan Dimon Bendtsen, Carsten Kallesøe, Carlos Ocampo-Martinez


Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

71 Downloads (Pure)


Many traditional control solutions in urban drainage networks suffer from unmodelled nonlinear effects such as rain and wastewater infiltrating the system. These effects are challenging and often too complex to capture through physical modelling without using a high number of flow sensors. In this article, we use level sensors and design a stochastic model predictive controller by combining nominal dynamics (hydraulics) with unknown nonlinearities (hydrology) modelled as Gaussian processes. The Gaussian process model provides residual uncertainties trained via the level measurements and captures the effect of the hydrologic load and the transport dynamics in the network. To show the practical effectiveness of the approach, we present the improvement of the closed-loop control performance on an experimental laboratory setup using real rain and wastewater flow data.
Titel2022 American Control Conference, ACC
Antal sider7
Publikationsdatosep. 2022
ISBN (Trykt)978-1-6654-5197-0, 978-1-6654-9480-9
ISBN (Elektronisk)978-1-6654-5196-3
StatusUdgivet - sep. 2022
Begivenhed2022 American Control Conference (ACC) -
Varighed: 8 jun. 202210 jun. 2022


Konference2022 American Control Conference (ACC)
NavnAnnual American Control Conference (ACC)


Dyk ned i forskningsemnerne om 'Learning-Based Predictive Control with Gaussian Processes: An Application to Urban Drainage Networks'. Sammen danner de et unikt fingeraftryk.