USE OF DATA MINING TECHNIQUES TO CHARACTERIZE MV CONSUMERS AND TO SUPPORT THE CONSUMER- SUPPLIER RELATIONSHIP
Sérgio Ramos, Zita Vale, Joao J. E. Santana, Fátima Rodrigues · 2006
This paper consists in the characterization of electric power profiles of medium voltage (MV) consumers, based on the data base knowledge discovery process. Data Mining techniques were used as sup- port for the agents of the electric power retail markets, with the purpose of obtaining specific knowledge of their customers' consumption habits. A hierarchical clustering algorithm is used in order to form the different customers' classes and to find a set of representative consumption patterns. A classification model was built that, when applied to new consumers, allows classifying them in one of the obtained classes. New tariff op- tions were also defined, taking into consideration the typical consumption profile of the class to which the customers belong. With the results obtained, the consequences that these will have in the interaction between customer and electric power suppliers are analyzed.