A Comprehensive Evaluation of Supervised Machine Learning for the Phase Identification Problem

Power distribution circuits undergo frequent network
topology changes that are often left undocumented. As a result, the
documentation of a circuit’s connectivity becomes inaccurate with
time. The lack of reliable circuit connectivity information is one of the
biggest obstacles to model, monitor, and control modern distribution
systems. To enhance the reliability and efficiency of electric power
distribution systems, the circuit’s connectivity information must be
updated periodically. This paper focuses on one critical component of
a distribution circuit’s topology - the secondary transformer to phase
association. This topology component describes the set of phase lines
that feed power to a given secondary transformer (and therefore a
given group of power consumers). Finding the documentation of this
component is call Phase Identification, and is typically performed
with physical measurements. These measurements can take time
lengths on the order of several months, but with supervised learning,
the time length can be reduced significantly. This paper compares
several such methods applied to Phase Identification for a large
range of real distribution circuits, describes a method of training
data selection, describes preprocessing steps unique to the Phase
Identification problem, and ultimately describes a method which
obtains high accuracy (> 96% in most cases, > 92% in the worst
case) using only 5% of the measurements typically used for Phase
Identification.

Authors:

• Brandon Foggo
• Nanpeng Yu

Keywords:

• Distribution network
• machine learning
• network topology
• phase identification
• smart grid.

References:

[1] C.-S. Chen, T.-T. Ku, and C.-H. Lin, “Design of phase identification
system to support three-phase loading balance of distribution feeders,”
IEEE Transactions on Industry Applications, vol. 48, no. 1, pp. 191–198,
2012.
[2] K. J. Caird, “Meter phase identification,” Mar. 27 2012, uS Patent
8,143,879.
[3] M. H. Wen, R. Arghandeh, A. von Meier, K. Poolla, and V. O. Li, “Phase
identification in distribution networks with micro-synchrophasors,” in
2015 IEEE Power & Energy Society General Meeting. IEEE, 2015,
pp. 1–5.
[4] M. Dilek, R. P. Broadwater, and R. Sequin, “Phase prediction in
distribution systems,” in Power Engineering Society Winter Meeting,
2002. IEEE, vol. 2, 2002, pp. 985–990.
[5] V. Arya, D. Seetharam, S. Kalyanaraman, K. Dontas, C. Pavlovski,
S. Hoy, and J. R. Kalagnanam, “Phase identification in smart
grids,” in Smart Grid Communications (SmartGridComm), 2011 IEEE
International Conference on, Oct 2011, pp. 25–30.
[6] H. Pezeshki and P. J. Wolfs, “Consumer phase identification in a three
phase unbalanced LV distribution network,” in 2012 3rd IEEE PES
Innovative Smart Grid Technologies Europe (ISGT Europe), Oct 2012,
pp. 1–7.
[7] T. A. Short, “Advanced metering for phase identification, transformer
identification, and secondary modeling,” IEEE Transactions on Smart
Grid, vol. 4, no. 2, pp. 651–658, June 2013.
[8] W. Wang, N. Yu, B. Foggo, J. Davis, and J. Li, “Phase identification
in electric power distribution systems by clustering of smart meter
data,” in Machine Learning and Applications (ICMLA), 2016 15th IEEE
International Conference on. IEEE, 2016, pp. 259–265.
[9] W. Wang, N. Yu, and Z. Lu, “Advanced metering infrastructure data
driven phase identification in smart grid,” GREEN 2017 Forward, pp.
16–23, 2017.
[10] C. M. Bishop, Pattern Recognition and Machine Learning (Information
Science and Statistics). Secaucus, NJ, USA: Springer-Verlag New York,
Inc., 2006.
[11] Y. Le Borgne, “Bias-variance trade-off characterization in a classification
problem: What differences with regression,” Machine Learning Group,
Univ. Libre de Bruxelles, Belgium, 2005.
[12] K. Hajebi, Y. Abbasi-Yadkori, H. Shahbazi, and H. Zhang, “Fast
approximate nearest-neighbor search with k-nearest neighbor graph,”
in IJCAI Proceedings-International Joint Conference on Artificial
Intelligence, vol. 22, no. 1, 2011, p. 1312.
[13] W.-Y. Loh, “Classification and regression tree methods,” Encyclopedia
of statistics in quality and reliability, 2008.
[14] B. P. Roe, H.-J. Yang, J. Zhu, Y. Liu, I. Stancu, and G. McGregor,
“Boosted decision trees as an alternative to artificial neural networks
for particle identification,” Nuclear Instruments and Methods in Physics
Research A, vol. 543, pp. 577–584, May 2005.
[15] S. Sonoda and N. Murata, “Neural network with unbounded activation
functions is universal approximator,” ArXiv e-prints, May 2015.
[16] D.-A. Clevert, T. Unterthiner, and S. Hochreiter, “Fast and accurate deep
network learning by exponential linear units (ELUs),” ArXiv e-prints,
Nov. 2015.
[17] G. Klambauer, T. Unterthiner, A. Mayr, and S. Hochreiter,
“Self-normalizing neural networks,” ArXiv e-prints, Jun. 2017.
[18] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. MIT Press,
2016, http://www.deeplearningbook.org.
[19] J. Lampinen and A. Vehtari, “Bayesian approach for neural
networksreview and case studies,” Neural networks, vol. 14, no. 3, pp.
257–274, 2001.
[20] D. M. Blei, A. Kucukelbir, and J. D. McAuliffe, “Variational inference:
A review for statisticians,” ArXiv e-prints, Jan. 2016.
[21] R. Ranganath, S. Gerrish, and D. Blei, “Black box variational inference,”
in Artificial Intelligence and Statistics, 2014, pp. 814–822.
[22] Y. Gal and Z. Ghahramani, “Dropout as a bayesian approximation:
Representing model uncertainty in deep learning,” in International
Conference on Machine Learning, 2016, pp. 1050–1059.
[23] H. Lin and J. Bilmes, “How to select a good training-data subset for
transcription: Submodular active selection for sequences,” Washington
University Seattle Dept. of Electrical Engineering, Tech. Rep., 2009.
[24] U. Von Luxburg, “A tutorial on spectral clustering,” Statistics and
computing, vol. 17, no. 4, pp. 395–416, 2007.
[25] A. Krause and D. Golovin, “Submodular function maximization.” 2014.