Keywords
water resource management, sectorization, leak detection, simulation, clustering
Start Date
1-7-2012 12:00 AM
Abstract
In this paper the main Decision Support functionalities proposed anddeveloped within the H2OLEAK research project are presented. H2OLEAK, cofoundedby Regione Lombardia in Italy, is aimed at designing and developing aninnovative technological platform for supporting a rational and integratedmanagement of urban water distribution systems. It integrates already availableand robust technological solutions, such as Supervisory Control And DataAcquisition (SCADA) systems, Geographical Information Systems (GIS) andBusiness Intelligence tools, with advanced analytical methodologies to supportmanagers in their decision making activities, enabling prompt and proactiveactions that may reduce costs while guaranteeing high customers satisfaction.In particular, computational approaches proposed to address three main problemsare described: (i) automatic districts identification to obtain the “optimal” partition ofa water distribution system into virtually independent sub-networks, (ii)computational localization of leaky pipelines through the analysis of flows andpressures measured at the entry points of each district and (iii) regression modelsfor estimating the loss intensity of the leak to improve localization effectiveness byfurther reducing the set of pipelines to be checked physically.
Simulation and Machine Learning Strategies for Enabling Integrated Water Resource Management: H2OLeak Project
In this paper the main Decision Support functionalities proposed anddeveloped within the H2OLEAK research project are presented. H2OLEAK, cofoundedby Regione Lombardia in Italy, is aimed at designing and developing aninnovative technological platform for supporting a rational and integratedmanagement of urban water distribution systems. It integrates already availableand robust technological solutions, such as Supervisory Control And DataAcquisition (SCADA) systems, Geographical Information Systems (GIS) andBusiness Intelligence tools, with advanced analytical methodologies to supportmanagers in their decision making activities, enabling prompt and proactiveactions that may reduce costs while guaranteeing high customers satisfaction.In particular, computational approaches proposed to address three main problemsare described: (i) automatic districts identification to obtain the “optimal” partition ofa water distribution system into virtually independent sub-networks, (ii)computational localization of leaky pipelines through the analysis of flows andpressures measured at the entry points of each district and (iii) regression modelsfor estimating the loss intensity of the leak to improve localization effectiveness byfurther reducing the set of pipelines to be checked physically.
