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 consists in a multilayer controller with three hierarchical layers: learning and planning layer, supervision and adaptation layer, and feedback control layer. Results of applyingthe proposedapproach to the Barcelona DWN show that the quasi-explicitnature of the proposedadaptive predictivecontrollerleads to improvethe computationaltime, especially when the complexityof the problemstructure can vary while tuning the receding horizons.

[1]  J. J. Kanet,et al.  Dynamic planned safety stocks in supply networks , 2010 .

[2]  Maciej Lawrynczuk.  Neural Models in Computationally Efficient Predictive Control Cooperating with Economic Optimisation , 2007, ICANN.

[3]  Reza Langari,et al.  Fuzzy Control: Synthesis and Analysis , 2000 .

[4]  Willy Wojsznis,et al.  Practical approach to tuning MPC. , 2003, ISA transactions.

[5]  Ignacio E. Grossmann,et al.  A model predictive control strategy for supply chain optimization , 2003, Comput. Chem. Eng..

[6]  Gabriela Cembrano,et al.  Improving water management efficiency by using optimization-based control strategies: the Barcelona case study , 2009 .

[7]  Haralambos Sarimveis,et al.  An adaptive model predictive control configuration for production-inventory systems , 2008 .

[8]  Sebastian Engell,et al.  Tuning MPC for desired closed-loop performance for MIMO systems , 2011, Proceedings of the 2011 American Control Conference.

[9]  Vicenç Puig,et al.  Operational Predictive Optimal Control of Barcelona Water Transport Network , 2011 .

[10]  François Anctil,et al.  Comparing Sigmoid Transfer Functions for Neural Network Multistep Ahead Streamflow Forecasting , 2010 .

[11]  Maciej Ławryńczuk,et al.  SOFT COMPUTING IN MODEL – BASED PREDICTIVE CONTROL † , 2006 .

[12]  Thomas Parisini,et al.  A receding-horizon regulator for nonlinear systems and a neural approximation , 1995, Autom..

[13]  M. Soroush,et al.  Model Predictive Control Tuning Methods: A Review , 2010 .

[14]  S. Joe Qin,et al.  A survey of industrial model predictive control technology , 2003 .

[15]  E. Ali,et al.  Heuristic On-Line Tuning for Nonlinear Model Predictive Controllers Using Fuzzy Logic , 2003 .

[16]  Vicenç Puig,et al.  Tuning of predictive controllers for drinking water networked systems , 2011 .

[17]  Valera GarcíaJuan José,et al.  Intelligent Multi-Objective Nonlinear Model Predictive Control (iMO-NMPC) , 2012 .

[18]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[19]  V Puig,et al.  Model predictive control of drinking water networks: A hierarchical and decentralized approach , 2010, Proceedings of the 2010 American Control Conference.

[20]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[21]  M. Babel,et al.  Identifying Prominent Explanatory Variables for Water Demand Prediction Using Artificial Neural Networks: A Case Study of Bangkok , 2011 .

[22]  Angelo Alessandri,et al.  Min-Max and Predictive Control for the Management of Distribution in Supply Chains , 2011, IEEE Transactions on Control Systems Technology.

[23]  João Vieira,et al.  Optimization of the Operation of Large-Scale Multisource Water-Supply Systems , 2011 .

[24]  Piotr Tatjewski,et al.  Soft computing in modelbased predictive control footnotemark , 2006 .

[25]  Martin T. Hagan,et al.  Gauss-Newton approximation to Bayesian learning , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[26]  Mikel Larrea,et al.  Intelligent Multi-Objective Nonlinear Model Predictive Control (iMO-NMPC): Towards the 'on-line' optimization of highly complex control problems , 2012, Expert Syst. Appl..

[27]  Rachid Ellaia,et al.  A continuous approach to combinatorial optimization: application of water system pump operations , 2012, Optim. Lett..

[28]  David E. Culler,et al.  Reducing Transient and Steady State Electricity Consumption in HVAC Using Learning-Based Model-Predictive Control , 2012, Proceedings of the IEEE.

[29]  M Casas,et al.  PLIO: a generic tool for real-time operational predictive optimal control of water networks. , 2011, Water science and technology : a journal of the International Association on Water Pollution Research.

[30]  C. J. Brouckaert,et al.  Optimal operation of water distribution networks by predictive control using MINLP , 2004 .

[31]  D.E. Rivera,et al.  Simulation-based optimal tuning of model predictive control policies for supply chain management using simultaneous perturbation stochastic approximation , 2006, 2006 American Control Conference.

[32]  Hannu T. Toivonen,et al.  A neural network model predictive controller , 2006 .

[33]  Toshio Fukuda,et al.  Theory and applications of neural networks for industrial control systems , 1992, IEEE Trans. Ind. Electron..

[34]  Jan M. Maciejowski,et al.  Predictive control : with constraints , 2002 .