Automating the Verification of the Low Voltage Network Cables and Topologies

Maizura Mokhtar, Valentin Robu, David Flynn, Ciaran Higgins, Jim Whyte, Caroline Loughran, Fiona Fulton

Research output: Contribution to journalArticle

Abstract

Low Voltage (LV) networks are increasingly required to cope with challenges they were not designed for, requiring for more active network management (ANM). Crucially, ANM solutions require the availability of accurate network information. In practice, available data on LV networks can be incomplete, a problem often overlooked in prior ANM research. For example, in the UK and many developed countries, the lifetime of distribution networks assets spans several decades, with some of the available asset data gathered and maintained over many years. This can often lead to incomplete cable data being available to network operators. To overcome this, we propose a novel machine learning technique to autonomously approximate the missing cable information in LV networks. Our proposed algorithm uses a tree-based search methodology, which approximates the missing cable’s cross section area (XSA) data based on rules engineers used when designing the LV networks. We validate our approach using a large database of real LV networks, where some of the cables’ XSA are treated as unknown and used as ground truth to evaluate the accuracy of the predictions. Moreover, we propose a mechanism that scores the confidence level of the prediction, information which is then presented to the human network planners.
Original languageEnglish
Number of pages10
JournalIEEE Transactions on Smart Grid
Early online date16 Sep 2019
DOIs
Publication statusE-pub ahead of print - 16 Sep 2019

Fingerprint

Cables
Active networks
Topology
Network management
Electric potential
Electric power distribution
Learning systems
Availability
Engineers

Cite this

Mokhtar, Maizura ; Robu, Valentin ; Flynn, David ; Higgins, Ciaran ; Whyte, Jim ; Loughran, Caroline ; Fulton, Fiona. / Automating the Verification of the Low Voltage Network Cables and Topologies. In: IEEE Transactions on Smart Grid. 2019.
@article{b35740c498394291ad8004a5a2cba310,
title = "Automating the Verification of the Low Voltage Network Cables and Topologies",
abstract = "Low Voltage (LV) networks are increasingly required to cope with challenges they were not designed for, requiring for more active network management (ANM). Crucially, ANM solutions require the availability of accurate network information. In practice, available data on LV networks can be incomplete, a problem often overlooked in prior ANM research. For example, in the UK and many developed countries, the lifetime of distribution networks assets spans several decades, with some of the available asset data gathered and maintained over many years. This can often lead to incomplete cable data being available to network operators. To overcome this, we propose a novel machine learning technique to autonomously approximate the missing cable information in LV networks. Our proposed algorithm uses a tree-based search methodology, which approximates the missing cable’s cross section area (XSA) data based on rules engineers used when designing the LV networks. We validate our approach using a large database of real LV networks, where some of the cables’ XSA are treated as unknown and used as ground truth to evaluate the accuracy of the predictions. Moreover, we propose a mechanism that scores the confidence level of the prediction, information which is then presented to the human network planners.",
author = "Maizura Mokhtar and Valentin Robu and David Flynn and Ciaran Higgins and Jim Whyte and Caroline Loughran and Fiona Fulton",
year = "2019",
month = "9",
day = "16",
doi = "10.1109/TSG.2019.2941722",
language = "English",
journal = "IEEE Transactions on Smart Grid",
issn = "1949-3053",
publisher = "IEEE",

}

Automating the Verification of the Low Voltage Network Cables and Topologies. / Mokhtar, Maizura; Robu, Valentin; Flynn, David; Higgins, Ciaran; Whyte, Jim; Loughran, Caroline; Fulton, Fiona.

In: IEEE Transactions on Smart Grid, 16.09.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automating the Verification of the Low Voltage Network Cables and Topologies

AU - Mokhtar, Maizura

AU - Robu, Valentin

AU - Flynn, David

AU - Higgins, Ciaran

AU - Whyte, Jim

AU - Loughran, Caroline

AU - Fulton, Fiona

PY - 2019/9/16

Y1 - 2019/9/16

N2 - Low Voltage (LV) networks are increasingly required to cope with challenges they were not designed for, requiring for more active network management (ANM). Crucially, ANM solutions require the availability of accurate network information. In practice, available data on LV networks can be incomplete, a problem often overlooked in prior ANM research. For example, in the UK and many developed countries, the lifetime of distribution networks assets spans several decades, with some of the available asset data gathered and maintained over many years. This can often lead to incomplete cable data being available to network operators. To overcome this, we propose a novel machine learning technique to autonomously approximate the missing cable information in LV networks. Our proposed algorithm uses a tree-based search methodology, which approximates the missing cable’s cross section area (XSA) data based on rules engineers used when designing the LV networks. We validate our approach using a large database of real LV networks, where some of the cables’ XSA are treated as unknown and used as ground truth to evaluate the accuracy of the predictions. Moreover, we propose a mechanism that scores the confidence level of the prediction, information which is then presented to the human network planners.

AB - Low Voltage (LV) networks are increasingly required to cope with challenges they were not designed for, requiring for more active network management (ANM). Crucially, ANM solutions require the availability of accurate network information. In practice, available data on LV networks can be incomplete, a problem often overlooked in prior ANM research. For example, in the UK and many developed countries, the lifetime of distribution networks assets spans several decades, with some of the available asset data gathered and maintained over many years. This can often lead to incomplete cable data being available to network operators. To overcome this, we propose a novel machine learning technique to autonomously approximate the missing cable information in LV networks. Our proposed algorithm uses a tree-based search methodology, which approximates the missing cable’s cross section area (XSA) data based on rules engineers used when designing the LV networks. We validate our approach using a large database of real LV networks, where some of the cables’ XSA are treated as unknown and used as ground truth to evaluate the accuracy of the predictions. Moreover, we propose a mechanism that scores the confidence level of the prediction, information which is then presented to the human network planners.

U2 - 10.1109/TSG.2019.2941722

DO - 10.1109/TSG.2019.2941722

M3 - Article

JO - IEEE Transactions on Smart Grid

JF - IEEE Transactions on Smart Grid

SN - 1949-3053

ER -