Electric customer classification using Nopfield recurrent ANN

In retail power markets precise information related to electric customers is of relevant interest. For efficient tariff design and pricing it is required accurate classification and segmentation of electric customers. In this paper, it is proposed a methodology for clustering electric customers based on a recurrent Hopfield Artificial Neural Network (H-ANN). In order to reduce the size of the input set of the clustering algorithm several filtering techniques are used. The effectiveness of the proposed approach is measured using characterization indexes. Results in a set of distribution customers are presented to demonstrate de efficiency of the approach.