One meter to find them all-water network leak localization using a single flow meter

Iyswarya Narayanan, Arunchandar Vasan, Venkatesh Sarangan, Anand Sivasubramaniam

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

Leak localization is a major issue faced by water utilities worldwide. Leaks are ideally detected and localized by a network-wide metering infrastructure. However, in many utilities, in-network metering is minimally present at just the inlets of subnetworks called District Metering Area (DMA). We consider the problem of leak localization using data from a single flow meter placed at the inlet of a DMA. We use standard time-series based modeling to detect if a current meter reading is a leak or not, and if so, to estimate the excess flow. Conventional approaches use an a-priori fully calibrated hydraulic model to map the excess flow back to a set of candidate leak locations. However, obtaining an accurate hydraulic model is expensive and hence, beyond the reach of many water utilities. We present an alternate approach that exploits the network structure and static properties in a novel way. Specifically, we extend the use of centrality metrics to infrastructure domains and use these metrics to map from the excess leak flow to the candidate leak location(s). We evaluate our approach on benchmark water utility network topologies as well as on real data obtained from an European water utility. On benchmark topologies, the localization obtained by our method is comparable to that obtained from a complete hydraulic model. On a real-world network, we were able to localize two out of the three leaks whose data we had access to. Of these two cases, we find that the actual leak location was in the candidate set identified by our approach; further, the approach pruned as much as 78% of the DMA locations, indicating a high degree of localization.

Original languageEnglish (US)
Title of host publicationIPSN 2014 - Proceedings of the 13th International Symposium on Information Processing in Sensor Networks (Part of CPS Week)
PublisherIEEE Computer Society
Pages47-58
Number of pages12
ISBN (Print)9781479931460
DOIs
StatePublished - Jan 1 2014
Event13th IEEE/ACM International Conference on Information Processing in Sensor Networks, IPSN 2014 - Berlin, Germany
Duration: Apr 15 2014Apr 17 2014

Publication series

NameIPSN 2014 - Proceedings of the 13th International Symposium on Information Processing in Sensor Networks (Part of CPS Week)

Other

Other13th IEEE/ACM International Conference on Information Processing in Sensor Networks, IPSN 2014
CountryGermany
CityBerlin
Period4/15/144/17/14

Fingerprint

Hydraulic models
Water
Topology
Time series

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications

Cite this

Narayanan, I., Vasan, A., Sarangan, V., & Sivasubramaniam, A. (2014). One meter to find them all-water network leak localization using a single flow meter. In IPSN 2014 - Proceedings of the 13th International Symposium on Information Processing in Sensor Networks (Part of CPS Week) (pp. 47-58). [6835794] (IPSN 2014 - Proceedings of the 13th International Symposium on Information Processing in Sensor Networks (Part of CPS Week)). IEEE Computer Society. https://doi.org/10.1109/IPSN.2014.6846740
Narayanan, Iyswarya ; Vasan, Arunchandar ; Sarangan, Venkatesh ; Sivasubramaniam, Anand. / One meter to find them all-water network leak localization using a single flow meter. IPSN 2014 - Proceedings of the 13th International Symposium on Information Processing in Sensor Networks (Part of CPS Week). IEEE Computer Society, 2014. pp. 47-58 (IPSN 2014 - Proceedings of the 13th International Symposium on Information Processing in Sensor Networks (Part of CPS Week)).
@inproceedings{5da27a9d37264217974c6f578afddcd8,
title = "One meter to find them all-water network leak localization using a single flow meter",
abstract = "Leak localization is a major issue faced by water utilities worldwide. Leaks are ideally detected and localized by a network-wide metering infrastructure. However, in many utilities, in-network metering is minimally present at just the inlets of subnetworks called District Metering Area (DMA). We consider the problem of leak localization using data from a single flow meter placed at the inlet of a DMA. We use standard time-series based modeling to detect if a current meter reading is a leak or not, and if so, to estimate the excess flow. Conventional approaches use an a-priori fully calibrated hydraulic model to map the excess flow back to a set of candidate leak locations. However, obtaining an accurate hydraulic model is expensive and hence, beyond the reach of many water utilities. We present an alternate approach that exploits the network structure and static properties in a novel way. Specifically, we extend the use of centrality metrics to infrastructure domains and use these metrics to map from the excess leak flow to the candidate leak location(s). We evaluate our approach on benchmark water utility network topologies as well as on real data obtained from an European water utility. On benchmark topologies, the localization obtained by our method is comparable to that obtained from a complete hydraulic model. On a real-world network, we were able to localize two out of the three leaks whose data we had access to. Of these two cases, we find that the actual leak location was in the candidate set identified by our approach; further, the approach pruned as much as 78{\%} of the DMA locations, indicating a high degree of localization.",
author = "Iyswarya Narayanan and Arunchandar Vasan and Venkatesh Sarangan and Anand Sivasubramaniam",
year = "2014",
month = "1",
day = "1",
doi = "10.1109/IPSN.2014.6846740",
language = "English (US)",
isbn = "9781479931460",
series = "IPSN 2014 - Proceedings of the 13th International Symposium on Information Processing in Sensor Networks (Part of CPS Week)",
publisher = "IEEE Computer Society",
pages = "47--58",
booktitle = "IPSN 2014 - Proceedings of the 13th International Symposium on Information Processing in Sensor Networks (Part of CPS Week)",
address = "United States",

}

Narayanan, I, Vasan, A, Sarangan, V & Sivasubramaniam, A 2014, One meter to find them all-water network leak localization using a single flow meter. in IPSN 2014 - Proceedings of the 13th International Symposium on Information Processing in Sensor Networks (Part of CPS Week)., 6835794, IPSN 2014 - Proceedings of the 13th International Symposium on Information Processing in Sensor Networks (Part of CPS Week), IEEE Computer Society, pp. 47-58, 13th IEEE/ACM International Conference on Information Processing in Sensor Networks, IPSN 2014, Berlin, Germany, 4/15/14. https://doi.org/10.1109/IPSN.2014.6846740

One meter to find them all-water network leak localization using a single flow meter. / Narayanan, Iyswarya; Vasan, Arunchandar; Sarangan, Venkatesh; Sivasubramaniam, Anand.

IPSN 2014 - Proceedings of the 13th International Symposium on Information Processing in Sensor Networks (Part of CPS Week). IEEE Computer Society, 2014. p. 47-58 6835794 (IPSN 2014 - Proceedings of the 13th International Symposium on Information Processing in Sensor Networks (Part of CPS Week)).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - One meter to find them all-water network leak localization using a single flow meter

AU - Narayanan, Iyswarya

AU - Vasan, Arunchandar

AU - Sarangan, Venkatesh

AU - Sivasubramaniam, Anand

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Leak localization is a major issue faced by water utilities worldwide. Leaks are ideally detected and localized by a network-wide metering infrastructure. However, in many utilities, in-network metering is minimally present at just the inlets of subnetworks called District Metering Area (DMA). We consider the problem of leak localization using data from a single flow meter placed at the inlet of a DMA. We use standard time-series based modeling to detect if a current meter reading is a leak or not, and if so, to estimate the excess flow. Conventional approaches use an a-priori fully calibrated hydraulic model to map the excess flow back to a set of candidate leak locations. However, obtaining an accurate hydraulic model is expensive and hence, beyond the reach of many water utilities. We present an alternate approach that exploits the network structure and static properties in a novel way. Specifically, we extend the use of centrality metrics to infrastructure domains and use these metrics to map from the excess leak flow to the candidate leak location(s). We evaluate our approach on benchmark water utility network topologies as well as on real data obtained from an European water utility. On benchmark topologies, the localization obtained by our method is comparable to that obtained from a complete hydraulic model. On a real-world network, we were able to localize two out of the three leaks whose data we had access to. Of these two cases, we find that the actual leak location was in the candidate set identified by our approach; further, the approach pruned as much as 78% of the DMA locations, indicating a high degree of localization.

AB - Leak localization is a major issue faced by water utilities worldwide. Leaks are ideally detected and localized by a network-wide metering infrastructure. However, in many utilities, in-network metering is minimally present at just the inlets of subnetworks called District Metering Area (DMA). We consider the problem of leak localization using data from a single flow meter placed at the inlet of a DMA. We use standard time-series based modeling to detect if a current meter reading is a leak or not, and if so, to estimate the excess flow. Conventional approaches use an a-priori fully calibrated hydraulic model to map the excess flow back to a set of candidate leak locations. However, obtaining an accurate hydraulic model is expensive and hence, beyond the reach of many water utilities. We present an alternate approach that exploits the network structure and static properties in a novel way. Specifically, we extend the use of centrality metrics to infrastructure domains and use these metrics to map from the excess leak flow to the candidate leak location(s). We evaluate our approach on benchmark water utility network topologies as well as on real data obtained from an European water utility. On benchmark topologies, the localization obtained by our method is comparable to that obtained from a complete hydraulic model. On a real-world network, we were able to localize two out of the three leaks whose data we had access to. Of these two cases, we find that the actual leak location was in the candidate set identified by our approach; further, the approach pruned as much as 78% of the DMA locations, indicating a high degree of localization.

UR - http://www.scopus.com/inward/record.url?scp=84904685552&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84904685552&partnerID=8YFLogxK

U2 - 10.1109/IPSN.2014.6846740

DO - 10.1109/IPSN.2014.6846740

M3 - Conference contribution

AN - SCOPUS:84904685552

SN - 9781479931460

T3 - IPSN 2014 - Proceedings of the 13th International Symposium on Information Processing in Sensor Networks (Part of CPS Week)

SP - 47

EP - 58

BT - IPSN 2014 - Proceedings of the 13th International Symposium on Information Processing in Sensor Networks (Part of CPS Week)

PB - IEEE Computer Society

ER -

Narayanan I, Vasan A, Sarangan V, Sivasubramaniam A. One meter to find them all-water network leak localization using a single flow meter. In IPSN 2014 - Proceedings of the 13th International Symposium on Information Processing in Sensor Networks (Part of CPS Week). IEEE Computer Society. 2014. p. 47-58. 6835794. (IPSN 2014 - Proceedings of the 13th International Symposium on Information Processing in Sensor Networks (Part of CPS Week)). https://doi.org/10.1109/IPSN.2014.6846740