Machine learning for the New York City power grid

Cynthia Rudin, David Waltz, Roger Anderson, Albert Boulanger, Ansaf Salleb-Aouissi, Maggie Chow, Haimonti Dutta, Philip Gross, Bert Huang, Steve Ierome, Delfina F. Isaac, Arthur Kressner, Rebecca Jane Passonneau, Axinia Radeva, Leon Wu

Research output: Contribution to journalArticle

108 Citations (Scopus)

Abstract

Power companies can benefit from the use of knowledge discovery methods and statistical machine learning for preventive maintenance. We introduce a general process for transforming historical electrical grid data into models that aim to predict the risk of failures for components and systems. These models can be used directly by power companies to assist with prioritization of maintenance and repair work. Specialized versions of this process are used to produce 1) feeder failure rankings, 2) cable, joint, terminator, and transformer rankings, 3) feeder Mean Time Between Failure (MTBF) estimates, and 4) manhole events vulnerability rankings. The process in its most general form can handle diverse, noisy, sources that are historical (static), semi-real-time, or real-time, incorporates state-of-the-art machine learning algorithms for prioritization (supervised ranking or MTBF), and includes an evaluation of results via cross-validation and blind test. Above and beyond the ranked lists and MTBF estimates are business management interfaces that allow the prediction capability to be integrated directly into corporate planning and decision support; such interfaces rely on several important properties of our general modeling approach: that machine learning features are meaningful to domain experts, that the processing of data is transparent, and that prediction results are accurate enough to support sound decision making. We discuss the challenges in working with historical electrical grid data that were not designed for predictive purposes. The rawness of these data contrasts with the accuracy of the statistical models that can be obtained from the process; these models are sufficiently accurate to assist in maintaining New York City's electrical grid.

Original languageEnglish (US)
Article number5770269
Pages (from-to)328-345
Number of pages18
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume34
Issue number2
DOIs
StatePublished - Jan 1 2012

Fingerprint

Learning systems
Machine Learning
Grid
Ranking
Data Grid
Prioritization
Industry
Preventive maintenance
Learning algorithms
Data mining
Cables
Repair
Real-time
Decision making
Statistical Learning
Preventive Maintenance
Acoustic waves
Prediction
Planning
Transformer

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics

Cite this

Rudin, C., Waltz, D., Anderson, R., Boulanger, A., Salleb-Aouissi, A., Chow, M., ... Wu, L. (2012). Machine learning for the New York City power grid. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(2), 328-345. [5770269]. https://doi.org/10.1109/TPAMI.2011.108
Rudin, Cynthia ; Waltz, David ; Anderson, Roger ; Boulanger, Albert ; Salleb-Aouissi, Ansaf ; Chow, Maggie ; Dutta, Haimonti ; Gross, Philip ; Huang, Bert ; Ierome, Steve ; Isaac, Delfina F. ; Kressner, Arthur ; Passonneau, Rebecca Jane ; Radeva, Axinia ; Wu, Leon. / Machine learning for the New York City power grid. In: IEEE Transactions on Pattern Analysis and Machine Intelligence. 2012 ; Vol. 34, No. 2. pp. 328-345.
@article{e0a28248da6d4430a4401b984530f4a7,
title = "Machine learning for the New York City power grid",
abstract = "Power companies can benefit from the use of knowledge discovery methods and statistical machine learning for preventive maintenance. We introduce a general process for transforming historical electrical grid data into models that aim to predict the risk of failures for components and systems. These models can be used directly by power companies to assist with prioritization of maintenance and repair work. Specialized versions of this process are used to produce 1) feeder failure rankings, 2) cable, joint, terminator, and transformer rankings, 3) feeder Mean Time Between Failure (MTBF) estimates, and 4) manhole events vulnerability rankings. The process in its most general form can handle diverse, noisy, sources that are historical (static), semi-real-time, or real-time, incorporates state-of-the-art machine learning algorithms for prioritization (supervised ranking or MTBF), and includes an evaluation of results via cross-validation and blind test. Above and beyond the ranked lists and MTBF estimates are business management interfaces that allow the prediction capability to be integrated directly into corporate planning and decision support; such interfaces rely on several important properties of our general modeling approach: that machine learning features are meaningful to domain experts, that the processing of data is transparent, and that prediction results are accurate enough to support sound decision making. We discuss the challenges in working with historical electrical grid data that were not designed for predictive purposes. The rawness of these data contrasts with the accuracy of the statistical models that can be obtained from the process; these models are sufficiently accurate to assist in maintaining New York City's electrical grid.",
author = "Cynthia Rudin and David Waltz and Roger Anderson and Albert Boulanger and Ansaf Salleb-Aouissi and Maggie Chow and Haimonti Dutta and Philip Gross and Bert Huang and Steve Ierome and Isaac, {Delfina F.} and Arthur Kressner and Passonneau, {Rebecca Jane} and Axinia Radeva and Leon Wu",
year = "2012",
month = "1",
day = "1",
doi = "10.1109/TPAMI.2011.108",
language = "English (US)",
volume = "34",
pages = "328--345",
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
issn = "0162-8828",
publisher = "IEEE Computer Society",
number = "2",

}

Rudin, C, Waltz, D, Anderson, R, Boulanger, A, Salleb-Aouissi, A, Chow, M, Dutta, H, Gross, P, Huang, B, Ierome, S, Isaac, DF, Kressner, A, Passonneau, RJ, Radeva, A & Wu, L 2012, 'Machine learning for the New York City power grid', IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 2, 5770269, pp. 328-345. https://doi.org/10.1109/TPAMI.2011.108

Machine learning for the New York City power grid. / Rudin, Cynthia; Waltz, David; Anderson, Roger; Boulanger, Albert; Salleb-Aouissi, Ansaf; Chow, Maggie; Dutta, Haimonti; Gross, Philip; Huang, Bert; Ierome, Steve; Isaac, Delfina F.; Kressner, Arthur; Passonneau, Rebecca Jane; Radeva, Axinia; Wu, Leon.

In: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 34, No. 2, 5770269, 01.01.2012, p. 328-345.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Machine learning for the New York City power grid

AU - Rudin, Cynthia

AU - Waltz, David

AU - Anderson, Roger

AU - Boulanger, Albert

AU - Salleb-Aouissi, Ansaf

AU - Chow, Maggie

AU - Dutta, Haimonti

AU - Gross, Philip

AU - Huang, Bert

AU - Ierome, Steve

AU - Isaac, Delfina F.

AU - Kressner, Arthur

AU - Passonneau, Rebecca Jane

AU - Radeva, Axinia

AU - Wu, Leon

PY - 2012/1/1

Y1 - 2012/1/1

N2 - Power companies can benefit from the use of knowledge discovery methods and statistical machine learning for preventive maintenance. We introduce a general process for transforming historical electrical grid data into models that aim to predict the risk of failures for components and systems. These models can be used directly by power companies to assist with prioritization of maintenance and repair work. Specialized versions of this process are used to produce 1) feeder failure rankings, 2) cable, joint, terminator, and transformer rankings, 3) feeder Mean Time Between Failure (MTBF) estimates, and 4) manhole events vulnerability rankings. The process in its most general form can handle diverse, noisy, sources that are historical (static), semi-real-time, or real-time, incorporates state-of-the-art machine learning algorithms for prioritization (supervised ranking or MTBF), and includes an evaluation of results via cross-validation and blind test. Above and beyond the ranked lists and MTBF estimates are business management interfaces that allow the prediction capability to be integrated directly into corporate planning and decision support; such interfaces rely on several important properties of our general modeling approach: that machine learning features are meaningful to domain experts, that the processing of data is transparent, and that prediction results are accurate enough to support sound decision making. We discuss the challenges in working with historical electrical grid data that were not designed for predictive purposes. The rawness of these data contrasts with the accuracy of the statistical models that can be obtained from the process; these models are sufficiently accurate to assist in maintaining New York City's electrical grid.

AB - Power companies can benefit from the use of knowledge discovery methods and statistical machine learning for preventive maintenance. We introduce a general process for transforming historical electrical grid data into models that aim to predict the risk of failures for components and systems. These models can be used directly by power companies to assist with prioritization of maintenance and repair work. Specialized versions of this process are used to produce 1) feeder failure rankings, 2) cable, joint, terminator, and transformer rankings, 3) feeder Mean Time Between Failure (MTBF) estimates, and 4) manhole events vulnerability rankings. The process in its most general form can handle diverse, noisy, sources that are historical (static), semi-real-time, or real-time, incorporates state-of-the-art machine learning algorithms for prioritization (supervised ranking or MTBF), and includes an evaluation of results via cross-validation and blind test. Above and beyond the ranked lists and MTBF estimates are business management interfaces that allow the prediction capability to be integrated directly into corporate planning and decision support; such interfaces rely on several important properties of our general modeling approach: that machine learning features are meaningful to domain experts, that the processing of data is transparent, and that prediction results are accurate enough to support sound decision making. We discuss the challenges in working with historical electrical grid data that were not designed for predictive purposes. The rawness of these data contrasts with the accuracy of the statistical models that can be obtained from the process; these models are sufficiently accurate to assist in maintaining New York City's electrical grid.

UR - http://www.scopus.com/inward/record.url?scp=84055217877&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84055217877&partnerID=8YFLogxK

U2 - 10.1109/TPAMI.2011.108

DO - 10.1109/TPAMI.2011.108

M3 - Article

C2 - 21576741

AN - SCOPUS:84055217877

VL - 34

SP - 328

EP - 345

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

IS - 2

M1 - 5770269

ER -

Rudin C, Waltz D, Anderson R, Boulanger A, Salleb-Aouissi A, Chow M et al. Machine learning for the New York City power grid. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2012 Jan 1;34(2):328-345. 5770269. https://doi.org/10.1109/TPAMI.2011.108