The increasing challenges of water scarcity and climate change need innovative digital solutions to enhance resilience, sustainability, and operational awareness of Water Distribution Systems (WDSs). This chapter presents an innovative perspective on the digital transformation of Smart Water Networks, integrating large-scale monitoring, Low-Power Wide-Area Network communications, physical modeling, and artificial intelligence. By connecting the physical infrastructure through an Internet of Things (IoT) network it is possible to achieve several data-driven ecosystem improvement and analytics. Within this framework, Digital Twin approaches are discussed as a mean to combine real-time measurements, hydraulic simulation, and machine learning for continuous monitoring and active system analysis. Graph-based representations and learning techniques are further examined as effective tools for modeling network structure and dynamics under sparse sensing conditions. The chapter also reviews data-driven methods for demand analysis, forecasting, and network monitoring, and illustrates their integration into operator-oriented platform.
Casalbore, M., Cattai, T., Garlisi, D., Pierluigi, L., Redemptor Jr Laceda, T., Pagano, A., et al. (2026). Digital Transformation of Resilient and Sustainable Smart Water Distribution Systems. In Telecommunications of the Future: A book of contributions from the RESTART program (pp. 973-1005).
Digital Transformation of Resilient and Sustainable Smart Water Distribution Systems
Domenico Garlisi;Antonino Pagano;
2026-01-12
Abstract
The increasing challenges of water scarcity and climate change need innovative digital solutions to enhance resilience, sustainability, and operational awareness of Water Distribution Systems (WDSs). This chapter presents an innovative perspective on the digital transformation of Smart Water Networks, integrating large-scale monitoring, Low-Power Wide-Area Network communications, physical modeling, and artificial intelligence. By connecting the physical infrastructure through an Internet of Things (IoT) network it is possible to achieve several data-driven ecosystem improvement and analytics. Within this framework, Digital Twin approaches are discussed as a mean to combine real-time measurements, hydraulic simulation, and machine learning for continuous monitoring and active system analysis. Graph-based representations and learning techniques are further examined as effective tools for modeling network structure and dynamics under sparse sensing conditions. The chapter also reviews data-driven methods for demand analysis, forecasting, and network monitoring, and illustrates their integration into operator-oriented platform.| File | Dimensione | Formato | |
|---|---|---|---|
|
WITS_book1.pdf
Solo gestori archvio
Descrizione: intero articolo
Tipologia:
Versione Editoriale
Dimensione
36.03 MB
Formato
Adobe PDF
|
36.03 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
|
WITS_book1-parte1-pp1-11.pdf
accesso aperto
Descrizione: parte 1
Tipologia:
Versione Editoriale
Dimensione
9.62 MB
Formato
Adobe PDF
|
9.62 MB | Adobe PDF | Visualizza/Apri |
|
WITS_book1-parte2-pp12-22.pdf
accesso aperto
Descrizione: parte 2
Tipologia:
Versione Editoriale
Dimensione
8.99 MB
Formato
Adobe PDF
|
8.99 MB | Adobe PDF | Visualizza/Apri |
|
WITS_book1-parte3-pp23-33.pdf
accesso aperto
Descrizione: parte 3
Tipologia:
Versione Editoriale
Dimensione
9.19 MB
Formato
Adobe PDF
|
9.19 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.


