Critical analysis of pattern recognition load curves using multi-layer perceptron neural network

Understanding energy consumption patterns is a very important task for a good operation of power system, such patterns can be studied through the history of load curves of a given system. In this study is proposed a methodology for classification of load curves based on the similarities of the patterns presented over the days of the week in which they were generated. For this, a Multi-Layer Perceptron (MLP) Artificial Neural Network (ANN) was used to perform the pattern recognition of load curves. The results show that the algorithm was able to find typical behaviors in the set of analyzed curves, classifying curves with similar patterns in matching groups.