A microservice architecture for leak localization in water distribution networks using hybrid AI
Up to 30% of all drinking water is wasted due to leaks in water distribution networks (WDNs). In times of drought and water shortage, wasting so much drinking water has a considerable environmental and financial cost. In this paper, we present a microservice architecture for leak localization in WDN...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IWA Publishing
2023-05-01
|
| Series: | Journal of Hydroinformatics |
| Subjects: | |
| Online Access: | http://jhydro.iwaponline.com/content/25/3/851 |
| _version_ | 1797200691770425344 |
|---|---|
| author | Ganjour Mazaev Michael Weyns Pieter Moens Pieter Jan Haest Filip Vancoillie Guido Vaes Joeri Debaenst Aagje Waroux Kris Marlein Femke Ongenae Sofie Van Hoecke |
| author_facet | Ganjour Mazaev Michael Weyns Pieter Moens Pieter Jan Haest Filip Vancoillie Guido Vaes Joeri Debaenst Aagje Waroux Kris Marlein Femke Ongenae Sofie Van Hoecke |
| author_sort | Ganjour Mazaev |
| collection | DOAJ |
| description | Up to 30% of all drinking water is wasted due to leaks in water distribution networks (WDNs). In times of drought and water shortage, wasting so much drinking water has a considerable environmental and financial cost. In this paper, we present a microservice architecture for leak localization in WDNs, where heterogeneous sources of data consisting of sensor measurements, Geographic Information System (GIS), and Customer Relationship Management (CRM) data are used to feed a leak monitoring solution which combines hybrid data-driven and model-based leak detection and localization methodologies. The solution is validated using in-field leak experiments in an operational WDN. The final leak probabilities are presented in a visualization dashboard. The search zone for most leaks is reduced to a few kilometers or less. For other leaks, the solution is able to indicate a larger search zone to reflect its higher leak prediction uncertainty.
HIGHLIGHTS
A microservice architecture for leak monitoring in WDNs is designed.;
Sensor measurements and GIS and CRM data are used for leak localization.;
A post-processing procedure is presented to combine leak location predictions of two hybrid model-based and data-driven methodologies.;
The architecture is evaluated using real leaks in an operational WDN.; |
| first_indexed | 2024-03-13T07:05:55Z |
| format | Article |
| id | doaj.art-d3cb660f665d439495f656ba95a5b923 |
| institution | Directory Open Access Journal |
| issn | 1464-7141 1465-1734 |
| language | English |
| last_indexed | 2024-04-24T07:35:41Z |
| publishDate | 2023-05-01 |
| publisher | IWA Publishing |
| record_format | Article |
| series | Journal of Hydroinformatics |
| spelling | doaj.art-d3cb660f665d439495f656ba95a5b9232024-04-20T06:29:24ZengIWA PublishingJournal of Hydroinformatics1464-71411465-17342023-05-0125385186610.2166/hydro.2023.147147A microservice architecture for leak localization in water distribution networks using hybrid AIGanjour Mazaev0Michael Weyns1Pieter Moens2Pieter Jan Haest3Filip Vancoillie4Guido Vaes5Joeri Debaenst6Aagje Waroux7Kris Marlein8Femke Ongenae9Sofie Van Hoecke10 IDLab, Ghent University – imec, 9052 Zwijnaarde, Belgium IDLab, Ghent University – imec, 9052 Zwijnaarde, Belgium IDLab, Ghent University – imec, 9052 Zwijnaarde, Belgium De Watergroep, 1000 Brussels, Belgium De Watergroep, 1000 Brussels, Belgium Hydroscan, 3010 Leuven, Belgium Hydroscan, 3010 Leuven, Belgium Itineris, 9000 Ghent, Belgium Itineris, 9000 Ghent, Belgium IDLab, Ghent University – imec, 9052 Zwijnaarde, Belgium IDLab, Ghent University – imec, 9052 Zwijnaarde, Belgium Up to 30% of all drinking water is wasted due to leaks in water distribution networks (WDNs). In times of drought and water shortage, wasting so much drinking water has a considerable environmental and financial cost. In this paper, we present a microservice architecture for leak localization in WDNs, where heterogeneous sources of data consisting of sensor measurements, Geographic Information System (GIS), and Customer Relationship Management (CRM) data are used to feed a leak monitoring solution which combines hybrid data-driven and model-based leak detection and localization methodologies. The solution is validated using in-field leak experiments in an operational WDN. The final leak probabilities are presented in a visualization dashboard. The search zone for most leaks is reduced to a few kilometers or less. For other leaks, the solution is able to indicate a larger search zone to reflect its higher leak prediction uncertainty. HIGHLIGHTS A microservice architecture for leak monitoring in WDNs is designed.; Sensor measurements and GIS and CRM data are used for leak localization.; A post-processing procedure is presented to combine leak location predictions of two hybrid model-based and data-driven methodologies.; The architecture is evaluated using real leaks in an operational WDN.;http://jhydro.iwaponline.com/content/25/3/851hybrid aihydraulicsleak localizationmachine learningmicroservicewater distribution network |
| spellingShingle | Ganjour Mazaev Michael Weyns Pieter Moens Pieter Jan Haest Filip Vancoillie Guido Vaes Joeri Debaenst Aagje Waroux Kris Marlein Femke Ongenae Sofie Van Hoecke A microservice architecture for leak localization in water distribution networks using hybrid AI Journal of Hydroinformatics hybrid ai hydraulics leak localization machine learning microservice water distribution network |
| title | A microservice architecture for leak localization in water distribution networks using hybrid AI |
| title_full | A microservice architecture for leak localization in water distribution networks using hybrid AI |
| title_fullStr | A microservice architecture for leak localization in water distribution networks using hybrid AI |
| title_full_unstemmed | A microservice architecture for leak localization in water distribution networks using hybrid AI |
| title_short | A microservice architecture for leak localization in water distribution networks using hybrid AI |
| title_sort | microservice architecture for leak localization in water distribution networks using hybrid ai |
| topic | hybrid ai hydraulics leak localization machine learning microservice water distribution network |
| url | http://jhydro.iwaponline.com/content/25/3/851 |
| work_keys_str_mv | AT ganjourmazaev amicroservicearchitectureforleaklocalizationinwaterdistributionnetworksusinghybridai AT michaelweyns amicroservicearchitectureforleaklocalizationinwaterdistributionnetworksusinghybridai AT pietermoens amicroservicearchitectureforleaklocalizationinwaterdistributionnetworksusinghybridai AT pieterjanhaest amicroservicearchitectureforleaklocalizationinwaterdistributionnetworksusinghybridai AT filipvancoillie amicroservicearchitectureforleaklocalizationinwaterdistributionnetworksusinghybridai AT guidovaes amicroservicearchitectureforleaklocalizationinwaterdistributionnetworksusinghybridai AT joeridebaenst amicroservicearchitectureforleaklocalizationinwaterdistributionnetworksusinghybridai AT aagjewaroux amicroservicearchitectureforleaklocalizationinwaterdistributionnetworksusinghybridai AT krismarlein amicroservicearchitectureforleaklocalizationinwaterdistributionnetworksusinghybridai AT femkeongenae amicroservicearchitectureforleaklocalizationinwaterdistributionnetworksusinghybridai AT sofievanhoecke amicroservicearchitectureforleaklocalizationinwaterdistributionnetworksusinghybridai AT ganjourmazaev microservicearchitectureforleaklocalizationinwaterdistributionnetworksusinghybridai AT michaelweyns microservicearchitectureforleaklocalizationinwaterdistributionnetworksusinghybridai AT pietermoens microservicearchitectureforleaklocalizationinwaterdistributionnetworksusinghybridai AT pieterjanhaest microservicearchitectureforleaklocalizationinwaterdistributionnetworksusinghybridai AT filipvancoillie microservicearchitectureforleaklocalizationinwaterdistributionnetworksusinghybridai AT guidovaes microservicearchitectureforleaklocalizationinwaterdistributionnetworksusinghybridai AT joeridebaenst microservicearchitectureforleaklocalizationinwaterdistributionnetworksusinghybridai AT aagjewaroux microservicearchitectureforleaklocalizationinwaterdistributionnetworksusinghybridai AT krismarlein microservicearchitectureforleaklocalizationinwaterdistributionnetworksusinghybridai AT femkeongenae microservicearchitectureforleaklocalizationinwaterdistributionnetworksusinghybridai AT sofievanhoecke microservicearchitectureforleaklocalizationinwaterdistributionnetworksusinghybridai |