Power Network Partitioning with a Fuzzy C-Means

Jeffrey Mezquita, Dalal Asber, Serge Lefebvre, Maarouf Saad, and Pierre J. Lagacé


Clustering, Fuzzy C-Means, Fuzzy Logic, Hydro-Québec


This paper presents an artificial intelligence methodology for partitioning a power network into coherent and completely connected areas. The proposed methodology uses Fuzzy C-Means and is based on an original concept in which competitive and LVQ neural networks are used to partition a power system. However, better clustering techniques exist and Fuzzy C-Means clustering has proven to be an effective way to cluster data. The methodology and the results obtained with the IEEE 39-bus and 118-bus systems, as well as with Hydro-Québec’s power network, are presented in this paper. The results show the effectiveness of this technique.

Important Links:

Go Back