Adaptive edge analytics for distributed networked control of water systems

Sokratis Kartakis, Weiren Yu, Reza Akhavan, Julie McCann

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

Abstract

Over the last decade, there has been a trend where water utility companies aim to make water distribution networks more intelligent in order to improve their quality of service, reduce water waste, minimize maintenance costs etc., by incorporating IoT technologies. Current state of the art solutions use expensive power hungry deployments to monitor and transmit water network states periodically in order to detect anomalous behaviors such as water leakage and bursts. However, more than 97% of water network assets are remote away from power and are often in geographically remote underpopulated areas, facts that make current approaches unsuitable for next generation more dynamic adaptive water networks. Battery-driven wireless sensor/actuator based solutions are theoretically the perfect choice to support next generation water distribution. In this paper, we present an end-to-end water leak localization system, which exploits edge processing and enables the use of battery-driven sensor nodes. Our system combines a lightweight edge anomaly detection algorithm based on compression rates and an efficient localization algorithm based on graph theory. The edge anomaly detection and localization elements of the systems produce a timely and accurate localization result and reduce the communication by 99% compared to the traditional periodic communication. We evaluated our schemes by deploying non-intrusive sensors measuring vibrational data on a real-world water test rig that have had controlled leakage and burst scenarios implemented.
Original languageEnglish
Title of host publicationProceedings : 2016 IEEE First International Conference on Internet-of-Things Design and Implementation, IoTDI 2016
Place of PublicationPiscataway, NJ (US)
PublisherIEEE
Pages72-82
Number of pages11
ISBN (Print)978-1-4673-9948-7
DOIs
Publication statusPublished - 19 May 2016
Event2016 IEEE 1st International Conference on Internet-of-Things Design and Implementation - Berlin, Germany
Duration: 4 Apr 20168 Apr 2016

Conference

Conference2016 IEEE 1st International Conference on Internet-of-Things Design and Implementation
Abbreviated titleIoTDI 2016
CountryGermany
CityBerlin
Period4/04/168/04/16

Fingerprint

Water
Edge detection
Graph theory
Communication
Sensors
Sensor nodes
Electric power distribution
Quality of service
Wastewater
Actuators
Processing
Costs
Industry

Bibliographical note

-© 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Keywords

  • IoT
  • cyber-physical systems
  • wireless sensor networks
  • anomaly detection
  • burst localization

Cite this

Kartakis, S., Yu, W., Akhavan, R., & McCann, J. (2016). Adaptive edge analytics for distributed networked control of water systems. In Proceedings : 2016 IEEE First International Conference on Internet-of-Things Design and Implementation, IoTDI 2016 (pp. 72-82). Piscataway, NJ (US): IEEE. https://doi.org/10.1109/IoTDI.2015.34
Kartakis, Sokratis ; Yu, Weiren ; Akhavan, Reza ; McCann, Julie. / Adaptive edge analytics for distributed networked control of water systems. Proceedings : 2016 IEEE First International Conference on Internet-of-Things Design and Implementation, IoTDI 2016. Piscataway, NJ (US) : IEEE, 2016. pp. 72-82
@inproceedings{9d7a22cc0c2c44b2b3d3d824acc1c93b,
title = "Adaptive edge analytics for distributed networked control of water systems",
abstract = "Over the last decade, there has been a trend where water utility companies aim to make water distribution networks more intelligent in order to improve their quality of service, reduce water waste, minimize maintenance costs etc., by incorporating IoT technologies. Current state of the art solutions use expensive power hungry deployments to monitor and transmit water network states periodically in order to detect anomalous behaviors such as water leakage and bursts. However, more than 97{\%} of water network assets are remote away from power and are often in geographically remote underpopulated areas, facts that make current approaches unsuitable for next generation more dynamic adaptive water networks. Battery-driven wireless sensor/actuator based solutions are theoretically the perfect choice to support next generation water distribution. In this paper, we present an end-to-end water leak localization system, which exploits edge processing and enables the use of battery-driven sensor nodes. Our system combines a lightweight edge anomaly detection algorithm based on compression rates and an efficient localization algorithm based on graph theory. The edge anomaly detection and localization elements of the systems produce a timely and accurate localization result and reduce the communication by 99{\%} compared to the traditional periodic communication. We evaluated our schemes by deploying non-intrusive sensors measuring vibrational data on a real-world water test rig that have had controlled leakage and burst scenarios implemented.",
keywords = "IoT, cyber-physical systems, wireless sensor networks, anomaly detection, burst localization",
author = "Sokratis Kartakis and Weiren Yu and Reza Akhavan and Julie McCann",
note = "-{\circledC} 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.",
year = "2016",
month = "5",
day = "19",
doi = "10.1109/IoTDI.2015.34",
language = "English",
isbn = "978-1-4673-9948-7",
pages = "72--82",
booktitle = "Proceedings : 2016 IEEE First International Conference on Internet-of-Things Design and Implementation, IoTDI 2016",
publisher = "IEEE",
address = "United States",

}

Kartakis, S, Yu, W, Akhavan, R & McCann, J 2016, Adaptive edge analytics for distributed networked control of water systems. in Proceedings : 2016 IEEE First International Conference on Internet-of-Things Design and Implementation, IoTDI 2016. IEEE, Piscataway, NJ (US), pp. 72-82, 2016 IEEE 1st International Conference on Internet-of-Things Design and Implementation, Berlin, Germany, 4/04/16. https://doi.org/10.1109/IoTDI.2015.34

Adaptive edge analytics for distributed networked control of water systems. / Kartakis, Sokratis; Yu, Weiren; Akhavan, Reza; McCann, Julie.

Proceedings : 2016 IEEE First International Conference on Internet-of-Things Design and Implementation, IoTDI 2016. Piscataway, NJ (US) : IEEE, 2016. p. 72-82.

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

TY - GEN

T1 - Adaptive edge analytics for distributed networked control of water systems

AU - Kartakis, Sokratis

AU - Yu, Weiren

AU - Akhavan, Reza

AU - McCann, Julie

N1 - -© 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2016/5/19

Y1 - 2016/5/19

N2 - Over the last decade, there has been a trend where water utility companies aim to make water distribution networks more intelligent in order to improve their quality of service, reduce water waste, minimize maintenance costs etc., by incorporating IoT technologies. Current state of the art solutions use expensive power hungry deployments to monitor and transmit water network states periodically in order to detect anomalous behaviors such as water leakage and bursts. However, more than 97% of water network assets are remote away from power and are often in geographically remote underpopulated areas, facts that make current approaches unsuitable for next generation more dynamic adaptive water networks. Battery-driven wireless sensor/actuator based solutions are theoretically the perfect choice to support next generation water distribution. In this paper, we present an end-to-end water leak localization system, which exploits edge processing and enables the use of battery-driven sensor nodes. Our system combines a lightweight edge anomaly detection algorithm based on compression rates and an efficient localization algorithm based on graph theory. The edge anomaly detection and localization elements of the systems produce a timely and accurate localization result and reduce the communication by 99% compared to the traditional periodic communication. We evaluated our schemes by deploying non-intrusive sensors measuring vibrational data on a real-world water test rig that have had controlled leakage and burst scenarios implemented.

AB - Over the last decade, there has been a trend where water utility companies aim to make water distribution networks more intelligent in order to improve their quality of service, reduce water waste, minimize maintenance costs etc., by incorporating IoT technologies. Current state of the art solutions use expensive power hungry deployments to monitor and transmit water network states periodically in order to detect anomalous behaviors such as water leakage and bursts. However, more than 97% of water network assets are remote away from power and are often in geographically remote underpopulated areas, facts that make current approaches unsuitable for next generation more dynamic adaptive water networks. Battery-driven wireless sensor/actuator based solutions are theoretically the perfect choice to support next generation water distribution. In this paper, we present an end-to-end water leak localization system, which exploits edge processing and enables the use of battery-driven sensor nodes. Our system combines a lightweight edge anomaly detection algorithm based on compression rates and an efficient localization algorithm based on graph theory. The edge anomaly detection and localization elements of the systems produce a timely and accurate localization result and reduce the communication by 99% compared to the traditional periodic communication. We evaluated our schemes by deploying non-intrusive sensors measuring vibrational data on a real-world water test rig that have had controlled leakage and burst scenarios implemented.

KW - IoT

KW - cyber-physical systems

KW - wireless sensor networks

KW - anomaly detection

KW - burst localization

UR - http://ieeexplore.ieee.org/document/7471352/

U2 - 10.1109/IoTDI.2015.34

DO - 10.1109/IoTDI.2015.34

M3 - Conference contribution

SN - 978-1-4673-9948-7

SP - 72

EP - 82

BT - Proceedings : 2016 IEEE First International Conference on Internet-of-Things Design and Implementation, IoTDI 2016

PB - IEEE

CY - Piscataway, NJ (US)

ER -

Kartakis S, Yu W, Akhavan R, McCann J. Adaptive edge analytics for distributed networked control of water systems. In Proceedings : 2016 IEEE First International Conference on Internet-of-Things Design and Implementation, IoTDI 2016. Piscataway, NJ (US): IEEE. 2016. p. 72-82 https://doi.org/10.1109/IoTDI.2015.34