Two-Stage Pattern Recognition of Load Curves for Classification of Electricity Customers

• Published in: IEEE transactions on power systems Vol. 22; no. 3; pp. 1120 - 1128
• Main Authors: Tsekouras, G.J., Hatziargyriou, N.D., Dialynas, E.N.
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.08.2007; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptive vector quantization; chronological load patterns; Classification; clustering; Clustering methods; Costs; customer classes; Customers; Electric power generation; Electric utilities; Electricity; Fuzzy; fuzzy k-means; hierarchical clustering; k-means; Load forecasting; Markets; Medium voltage; Methodology; Pattern recognition; Performance evaluation; Power engineering and energy; Power engineering computing; Power systems; Studies; Vector quantization
• ISSN: 0885-8950; 1558-0679
• DOI: 10.1109/TPWRS.2007.901287

This paper describes a two-stage methodology that was developed for the classification of electricity customers. It is based on pattern recognition methods, such as k-means, Kohonen adaptive vector quantization, fuzzy k-means, and hierarchical clustering, which are theoretically described and properly adapted. In the first stage, typical chronological load curves of various customers are estimated using pattern recognition methods, and their results are compared using six adequacy measures. In the second stage, classification of customers is performed by the same methods and measures, together with the representative load patterns of customers being obtained from the first stage. The results of the first stage can be used for load forecasting of customers and determination of tariffs. The results of the second stage provide valuable information for electricity suppliers in competitive energy markets. The developed methodology is applied on a set of medium voltage customers of the Greek power system, and the obtained results are presented and discussed.