Classification of total load demand profiles for war-ships based on pattern recognition methods

  • Authors:

  • G. J. Tsekouras;I. S. Karanasiou;F. D. Kanellos

  • Affiliations:

  • Department of Electrical & Computer Science, Hellenic Naval Academy, Piraeus;Informatics and Computer Science LAB, Department of Mathematics & Engineering Sciences, Univ. of Military Education, Hellenic Army Academy, Athens, Greece;Hellenic Transmission System Operator, Piraeus

  • Venue:
  • CIT'11 Proceedings of the 5th WSEAS international conference on Communications and information technology
  • Year:
  • 2011

Quantified Score

Hi-index 0.01

Visualization

Abstract

The classification of total load demand profiles for every type of war-ships is crucial information, because it is the necessary base for a series of studies and operations, such as load estimation, load shedding and power management systems. In this paper a pattern recognition methodology is presented, which is based on different pattern recognition methods, such as k-means, modified k-means etc. Each method can properly be optimized by using different adequacy measures, such as the ratio of within cluster sum of squares to between cluster variation. This methodology is applied to total load demand of Hellenic Navy MEKO type frigate indicatively and the usefulness of the respective results for the power system design and operation is proved.