Learning-based tuning of supervisory model predictive control for drinking water networks

This paper presents a constrained Model Predictive Control (MPC) strategy enriched with soft-control techniques as neural networks and fuzzy logic, to incorporate self-tuning capabilities and reliability aspects for the management of drinking water networks (DWNs). The control system architecture co...

Descripción completa

Detalles Bibliográficos
Autores: Grosso, J. M., Ocampo-Martínez, Carlos, Puig, Vicenç
Tipo de recurso: artículo
Estado:Versión enviada para evaluación y publicación
Fecha de publicación:2013
País:España
Institución:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/96417
Acceso en línea:http://hdl.handle.net/10261/96417
Access Level:acceso abierto
Palabra clave:Multilayer controller
Self-tuning
Neural networks
Drinking water networks
Fuzzy-logic
Model predictive control
Descripción
Sumario:This paper presents a constrained Model Predictive Control (MPC) strategy enriched with soft-control techniques as neural networks and fuzzy logic, to incorporate self-tuning capabilities and reliability aspects for the management of drinking water networks (DWNs). The control system architecture consists in a multilayer controller with three hierarchical layers: learning and planning layer, supervision and adaptation layer, and feedback control layer. Results of applying the proposed approach to the Barcelona DWN show that the quasi-explicit nature of the proposed adaptive predictive controller leads to improve the computational time, especially when the complexity of the problem structure can vary while tuning the receding horizons. © 2013 Elsevier Ltd.