Stochastic model predictive control based on Gaussian processes applied to drinking water networks

This study focuses on developing a stochastic model predictive control (MPC) strategy based on Gaussian processes (GPs) for propagating system disturbances in a receding horizon way. Using a probabilistic system representation, the state trajectories considering the influence of disturbances can be...

Descripción completa

Detalles Bibliográficos
Autores: Wang, Ye|||0000-0003-1395-1676, Ocampo-Martínez, Carlos|||0000-0001-9251-6044, Puig Cayuela, Vicenç|||0000-0002-6364-6429
Tipo de recurso: artículo
Fecha de publicación:2016
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/89276
Acceso en línea:https://hdl.handle.net/2117/89276
https://dx.doi.org/10.1049/iet-cta.2015.0657
Access Level:acceso abierto
Palabra clave:automation
control theory
optimisation
stochastic model predictive control
Gaussian processes
disturbance forecasting
drinking water networks
Classificació INSPEC::Control theory
Àrees temàtiques de la UPC::Informàtica::Automàtica i control
Descripción
Sumario:This study focuses on developing a stochastic model predictive control (MPC) strategy based on Gaussian processes (GPs) for propagating system disturbances in a receding horizon way. Using a probabilistic system representation, the state trajectories considering the influence of disturbances can be obtained through the uncertainty propagation by using GPs. This fact allows obtaining the confidence intervals for state evolutions over the MPC prediction horizon that are included into the MPC objective function and constraints. The feasibility of the proposed MPC strategy considering the incorporated results of disturbance forecasting is also discussed. Simulation results obtained from the application of the proposed approach to the Barcelona drinking water network taking real demand data into account are presented. The comparison with the well-known certainty-equivalent MPC shows the effectiveness of the proposed stochastic MPC approach.