Characterization and identification of electrical customers through the use of self-organizing maps and daily load parameters
MetadataShow full item record
AuthorValero Verdú, Sergio; Ortiz García, Mario; García Franco, Francisco J.; Encinas Redondo, Nuria; Gabaldón Marín, Antonio; [et al.]
Knowledge AreaIngeniería Eléctrica
PublisherIEEE Power & Energy Society (PES)
Bibliographic CitationVALERO VERDÚ, Sergio, ORTÍZ GARCÍA, Mario, ENCINAS, Nuria, GABALDÓN MARÍN, Antonio, MOLINA GARCÍA, Ángel, GÓMEZ LÁZARO, Emilio. Characterization and identification of electrical customers through the use of self-organizing maps and daily load parameters. En: Power Systems Conference and Exposition ( 2004: New York ). IEEE PES. Power Systems Conference & Exposition. 10-13 October, 2004. New York: IEEE Power & Energy Society. 2004. vol. 2. 899- 906 p.
KeywordsRedes neuronales artificiales
Segmentación de clientes eléctricos
Agregación de cliente
Artificial neural networks
Electrical customer segmentation
This paper shows the capacity of modern computational techniques such as the self-organizing map (SOM) as a methodology to achieve the classification of the electrical customers in a commercial or geographical area. This approach allows to extract the pattern of customer behavior from historic load demand series. Several ways of data analysis from load curves can be used to get different input data to “feed” the neural network. In this work, we propose two methods to improve customer clustering: the use of frequency-based indices and the use of the hourly load curve. Results of a case study developed on a set of different spanish customers and a comparison between the two approachs proposed here are presented.
The following license files are associated with this item: