The Community for Technology Leaders
Green Image
Issue No. 02 - February (2012 vol. 34)
ISSN: 0162-8828
pp: 328-345
A. Radeva , Center for Comput. Learning Syst., Columbia Univ., New York, NY, USA
L. Wu , Center for Comput. Learning Syst., Columbia Univ., New York, NY, USA
R. J. Passonneau , Center for Comput. Learning Syst., Columbia Univ., New York, NY, USA
D. F. Isaac , Consolidated Edison Co. of New York, New York, NY, USA
A. Kressner , Grid Connections, LLC, Consolidated Edison Co. of New York, New York, NY, USA
S. Ierome , Consolidated Edison Co. of New York, New York, NY, USA
P. N. Gross , Center for Comput. Learning Syst., Columbia Univ., New York, NY, USA
B. Huang , Center for Comput. Learning Syst., Columbia Univ., New York, NY, USA
H. Dutta , Center for Comput. Learning Syst., Columbia Univ., New York, NY, USA
M. Chow , Consolidated Edison Co. of New York, New York, NY, USA
A. Salleb-Aouissi , Center for Comput. Learning Syst., Columbia Univ., New York, NY, USA
A. Boulanger , Center for Comput. Learning Syst., Columbia Univ., New York, NY, USA
R. N. Anderson , Center for Comput. Learning Syst., Columbia Univ., New York, NY, USA
D. Waltz , Center for Comput. Learning Syst., Columbia Univ., New York, NY, USA
C. Rudin , MIT Sloan Sch. of Manage., Massachusetts Inst. of Technol., Cambridge, MA, USA
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.
INDEX TERMS
statistical analysis, learning (artificial intelligence), power engineering computing, power grids, statistical models, New York City power grid, power companies, knowledge discovery methods, statistical machine learning, preventive maintenance, electrical grid data, feeder failure rankings, transformer rankings, feeder Mean Time Between Failure, MTBF, manhole events vulnerability rankings, decision making, Maintenance engineering, Power cables, Data models, Power grids, Machine learning, reliability., Applications of machine learning, electrical grid, smart grid, knowledge discovery, supervised ranking, computational sustainability
CITATION
A. Radeva, L. Wu, R. J. Passonneau, D. F. Isaac, A. Kressner, S. Ierome, P. N. Gross, B. Huang, H. Dutta, M. Chow, A. Salleb-Aouissi, A. Boulanger, R. N. Anderson, D. Waltz, C. Rudin, "Machine Learning for the New York City Power Grid", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 34, no. , pp. 328-345, February 2012, doi:10.1109/TPAMI.2011.108
171 ms
(Ver 3.1 (10032016))