Application of Fuzzy C-Means for Proactive Clustering of Electrical Power Systems

Clustering of electrical power systems can be used to analyze their stability and state estimation assessments. In emergency scenarios, correct splitting of power systems (Controlled Islanding) might be essential to avoid wide-area blackout scenarios and to ensure a secure and continuous power supply. Based on power flow calculation, possible proactive clustering variants were defined to set appropriate constraints to the clustering criteria, which were examined via a dynamic simulation to test their validity. To decrease clustering ambiguity, Spectral Clustering based on fuzzy c-means algorithm was applied and clustering quality was increased.

[1]  Chi-Jui Wu,et al.  Analysis of Taiwan power system dynamic performance and coherency identification of synchronous generators using fuzzy c-means clustering , 2011, SICE Annual Conference 2011.

[2]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[3]  V. J. Rayward-Smith,et al.  Fuzzy Cluster Analysis: Methods for Classification, Data Analysis and Image Recognition , 1999 .

[4]  Mohammed Mahdi,et al.  Defensive islanding using self-organizing maps neural networks and hierarchical clustering , 2015, 2015 IEEE Eindhoven PowerTech.

[5]  G.T. Heydt,et al.  Slow-Coherency-Based Controlled Islanding—A Demonstration of the Approach on the August 14, 2003 Blackout Scenario , 2006, IEEE Transactions on Power Systems.

[6]  Ka Wing Chan,et al.  Identification of the vulnerable transmission segment and cluster of critical machines using line transient potential energy , 2007 .

[7]  Vladimir Terzija,et al.  On implementing a spectral clustering controlled islanding algorithm in real power systems , 2013, 2013 IEEE Grenoble Conference.

[8]  Jürgen Götze,et al.  Clustering of electrical transmission systems based on network topology and stability , 2015 .

[9]  R. Dunn,et al.  Determination of coherent clusters in a multi-machine power system based on wide-area signal measurements , 2010, IEEE PES General Meeting.

[10]  Kalyan K. Sen,et al.  Power Flow Control Concepts , 2009 .

[11]  Jürgen Götze,et al.  New applications for wide-area monitoring, protection and control , 2012, 2012 3rd IEEE PES Innovative Smart Grid Technologies Europe (ISGT Europe).

[12]  Yair Weiss,et al.  Segmentation using eigenvectors: a unifying view , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[13]  M. Davodi,et al.  Coherency approach by hybrid PSO, K-Means clustering method in power system , 2008, 2008 IEEE 2nd International Power and Energy Conference.

[14]  A. Nuhanovic,et al.  Validation of a clustering algorithm for voltage stability analysis on the Bosnian electric power system , 1998 .

[15]  Pei-Hwa Huang,et al.  Fuzzy c-means clustering for power system coherency , 2005, 2005 IEEE International Conference on Systems, Man and Cybernetics.

[16]  C. Rehtanz,et al.  About the relationship of line overload cascading and loss of synchronism in electric power systems , 2015, 2015 IEEE Eindhoven PowerTech.

[17]  Mita Nasipuri,et al.  A spatial fuzzy C-means algorithm with application to MRI image segmentation , 2015, 2015 Eighth International Conference on Advances in Pattern Recognition (ICAPR).

[18]  V. Vittal,et al.  System islanding using minimal cutsets with minimum net flow , 2004, IEEE PES Power Systems Conference and Exposition, 2004..

[19]  Turgay Yalcin,et al.  Detection of blackouts by using K-means clustering in a power system , 2012 .