Data Mining techniques application in Power Distribution utilities

This paper presents an electricity medium voltage (MV) consumer characterization framework supported on the data base knowledge discovery process (KDD). Data Mining (DM) techniques are used to discover a set of a MV consumer typical load profile and, therefore, to extract knowledge concerning to the electric energy consumption patterns. In order to form the different customers' classes a hierarchical clustering algorithm is used. The framework includes several steps, starting from the pre-processing data, application of DM algorithms, classification model, and finally, the interpretation of the discovered knowledge. To validate the proposed framework, a case study which includes real databases of MV consumers is used.