Data-Enabled Predictive Control for Optimal Pressure Management

Recent developments in control theory coupled with the growing availability of real-time data have paved the way for improved data-driven control methodologies. This study explores the application of a data-enabled predictive control (DeePC) algorithm to optimize the operation of water distribution...

Full description

Saved in:
Bibliographic Details
Main Authors: Gal Perelman, Avi Ostfeld
Format: Article
Language:English
Published: MDPI AG 2024-08-01
Series:Engineering Proceedings
Subjects:
Online Access:https://www.mdpi.com/2673-4591/69/1/5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850205459062980608
author Gal Perelman
Avi Ostfeld
author_facet Gal Perelman
Avi Ostfeld
author_sort Gal Perelman
collection DOAJ
description Recent developments in control theory coupled with the growing availability of real-time data have paved the way for improved data-driven control methodologies. This study explores the application of a data-enabled predictive control (DeePC) algorithm to optimize the operation of water distribution systems (WDS). WDSs are characterized by inherent uncertainties and complex nonlinear dynamics. Hence, classic control strategies that involve physical model-based methods are often hard to implement and infeasible to scale. The DeePC method suggests a paradigm shift by utilizing a data-driven approach. This method employs real-time data to dynamically learn an unknown system’s behavior. It utilizes a finite set of input–output samples (control settings, and measured data) to derive optimal policies, effectively bypassing the need for an explicit mathematical model of the system. In this study, DeePC is applied to a pressure management case study and demonstrates superior performance compared to standard control strategies.
format Article
id doaj-art-2f7e3b892f454e8593d63f5b986783f9
institution OA Journals
issn 2673-4591
language English
publishDate 2024-08-01
publisher MDPI AG
record_format Article
series Engineering Proceedings
spelling doaj-art-2f7e3b892f454e8593d63f5b986783f92025-08-20T02:11:05ZengMDPI AGEngineering Proceedings2673-45912024-08-01691510.3390/engproc2024069005Data-Enabled Predictive Control for Optimal Pressure ManagementGal Perelman0Avi Ostfeld1Faculty of Civil and Environmental Engineering, Technion—Israel Institute of Technology, Haifa 32000, IsraelFaculty of Civil and Environmental Engineering, Technion—Israel Institute of Technology, Haifa 32000, IsraelRecent developments in control theory coupled with the growing availability of real-time data have paved the way for improved data-driven control methodologies. This study explores the application of a data-enabled predictive control (DeePC) algorithm to optimize the operation of water distribution systems (WDS). WDSs are characterized by inherent uncertainties and complex nonlinear dynamics. Hence, classic control strategies that involve physical model-based methods are often hard to implement and infeasible to scale. The DeePC method suggests a paradigm shift by utilizing a data-driven approach. This method employs real-time data to dynamically learn an unknown system’s behavior. It utilizes a finite set of input–output samples (control settings, and measured data) to derive optimal policies, effectively bypassing the need for an explicit mathematical model of the system. In this study, DeePC is applied to a pressure management case study and demonstrates superior performance compared to standard control strategies.https://www.mdpi.com/2673-4591/69/1/5water distribution systemspredictive controldata-drivenuncertaintyreal-time
spellingShingle Gal Perelman
Avi Ostfeld
Data-Enabled Predictive Control for Optimal Pressure Management
Engineering Proceedings
water distribution systems
predictive control
data-driven
uncertainty
real-time
title Data-Enabled Predictive Control for Optimal Pressure Management
title_full Data-Enabled Predictive Control for Optimal Pressure Management
title_fullStr Data-Enabled Predictive Control for Optimal Pressure Management
title_full_unstemmed Data-Enabled Predictive Control for Optimal Pressure Management
title_short Data-Enabled Predictive Control for Optimal Pressure Management
title_sort data enabled predictive control for optimal pressure management
topic water distribution systems
predictive control
data-driven
uncertainty
real-time
url https://www.mdpi.com/2673-4591/69/1/5
work_keys_str_mv AT galperelman dataenabledpredictivecontrolforoptimalpressuremanagement
AT aviostfeld dataenabledpredictivecontrolforoptimalpressuremanagement