Phase Identification in Electric Power Distribution Systems by Clustering of Smart Meter Data

Accurate network and phase connectivity models are crucial to distribution system analytics, operations and planning. Although network connectivity information is mostly reliable, phase connectivity data is typically missing or erroneous. In this paper, an innovative phase identification algorithm is developed by clustering of voltage time series gathered from smart meters. The feature-based clustering approach is adopted where principal component analysis is first carried out to extract feature vectors from the raw time series. A constrained k-means clustering algorithm is then executed to separate customers/smart meters into various phase connectivity groups. The algorithm is applied on a real distribution feeder in Southern California Edison's service territory. The accuracy of the proposed algorithm is over 90%.

[1]  William Kersting,et al.  Distribution System Modeling and Analysis , 2001, Electric Power Generation, Transmission, and Distribution: The Electric Power Engineering Handbook.

[2]  Gene H. Golub,et al.  Matrix computations (3rd ed.) , 1996 .

[3]  J. A. Hartigan,et al.  A k-means clustering algorithm , 1979 .

[4]  Carla E. Brodley,et al.  Proceedings of the twenty-first international conference on Machine learning , 2004, International Conference on Machine Learning.

[5]  Murat Dilek,et al.  Integrated Design of Electrical Distribution Systems: Phase Balancing and Phase Prediction Case Studies , 2001 .

[6]  Robert H. Halstead,et al.  Matrix Computations , 2011, Encyclopedia of Parallel Computing.

[7]  David K. Smith.  Theory of Linear and Integer Programming , 1987 .

[8]  I. Jolliffe.  Principal Component Analysis , 2002 .

[9]  Joachim M. Buhmann,et al.  Learning with constrained and unlabelled data , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[10]  Tom A. Short,et al.  Advanced Metering for Phase Identification, Transformer Identification, and Secondary Modeling , 2013, IEEE Transactions on Smart Grid.

[11]  Fred Denny,et al.  Distribution System Modeling and Analysis , 2001 .

[12]  Claire Cardie,et al.  Proceedings of the Eighteenth International Conference on Machine Learning, 2001, p. 577–584. Constrained K-means Clustering with Background Knowledge , 2022 .

[13]  Claire Cardie,et al.  Clustering with Instance-Level Constraints , 2000, AAAI/IAAI.

[14]  Alexander Schrijver,et al.  Theory of linear and integer programming , 1986, Wiley-Interscience series in discrete mathematics and optimization.

[15]  Houman Pezeshki,et al.  Correlation based method for phase identification in a three phase LV distribution network , 2012, 2012 22nd Australasian Universities Power Engineering Conference (AUPEC).

[16]  P. Boesiger,et al.  A new correlation‐based fuzzy logic clustering algorithm for FMRI , 1998, Magnetic resonance in medicine.

[17]  Vijay Arya,et al.  Phase identification in smart grids , 2011, 2011 IEEE International Conference on Smart Grid Communications (SmartGridComm).

[18]  Kameshwar Poolla,et al.  Phase identification in distribution networks with micro-synchrophasors , 2015, 2015 IEEE Power & Energy Society General Meeting.

[19]  Ian T. Jolliffe,et al.  Principal Component Analysis , 2002, International Encyclopedia of Statistical Science.

[20]  T. Warren Liao,et al.  Clustering of time series data - a survey , 2005, Pattern Recognit..

[21]  Raymond J. Mooney,et al.  Integrating constraints and metric learning in semi-supervised clustering , 2004, ICML.