Power system typical load profiles using a new pattern recognition methodology

  • Authors:

  • G. J. Tsekouras;F. D. Kanellos;V. T. Kontargyri;E. S. Karanasiou;A. D. Salis;N. E. Mastorakis

  • Affiliations:

  • School of Electrical and Computer Engineering, National Technical University of Athens, Zografou, Athens, Greece and Department of Computer Science, Hellenic Naval Academy, Piraeus, Greece;School of Electrical and Computer Engineering, National Technical University of Athens, Zografou, Athens, Greece and Department of Computer Science, Hellenic Naval Academy, Piraeus, Greece;School of Electrical and Computer Engineering, National Technical University of Athens, Zografou, Athens, Greece and Department of Computer Science, Hellenic Naval Academy, Piraeus, Greece;School of Electrical and Computer Engineering, National Technical University of Athens, Zografou, Athens, Greece;School of Electrical and Computer Engineering, National Technical University of Athens, Zografou, Athens, Greece;Department of Computer Science, Hellenic Naval Academy, Piraeus, Greece

  • Venue:
  • ICC'08 Proceedings of the 12th WSEAS international conference on Circuits
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper a new pattern recognition methodology is described for the classification of the daily chronological load curves of power systems, in order to estimate their respective representative daily load profiles. It is based on pattern recognition methods, such as k-means, fuzzy k-means and hierarchical clustering, which are properly adapted. The parameters of each clustering method are properly selected by an optimization process using the ratio of within cluster sum of squares to between cluster variation (WCBCR) as an adequacy measure. This methodology is applied for the Greek power system, from which is proved that the separation between work days and non-work days for each season is not so enough descriptive.