Intelligent Techniques for Identification of Zones with Similar Wind Patterns

José Palomares-Salas; Agustín Agüera-Pérez; Juan González de la Rosa

IT Revolutions. Third International ICST Conference, Córdoba, Spain, March 23-25, 2011, Revised Selected Papers

Research Article

Intelligent Techniques for Identification of Zones with Similar Wind Patterns

Download

396 downloads

Cite: BibTeX Plain Text

@INPROCEEDINGS{10.1007/978-3-642-32304-1_2,
    author={Jos\^{e} Palomares-Salas and Agust\^{\i}n Ag\'{y}era-P\^{e}rez and Juan Gonz\^{a}lez de la Rosa},
    title={Intelligent Techniques for Identification of Zones with Similar Wind Patterns},
    proceedings={IT Revolutions. Third International ICST Conference, C\^{o}rdoba, Spain, March 23-25, 2011, Revised Selected Papers},
    proceedings_a={IT REVOLUTIONS},
    year={2012},
    month={10},
    keywords={Cluster Analysis Clustering Applications Data Mining Self-Organizing Feature Map},
    doi={10.1007/978-3-642-32304-1_2}
}

José Palomares-Salas
Agustín Agüera-Pérez
Juan González de la Rosa
Year: 2012
Intelligent Techniques for Identification of Zones with Similar Wind Patterns
IT REVOLUTIONS
Springer
DOI: 10.1007/978-3-642-32304-1_2

José Palomares-Salas^,*, Agustín Agüera-Pérez^,*, Juan González de la Rosa^,*

*Contact email: josecarlos.palomares@uca.es, agustin.aguera@uca.es, juanjose.delarosa@uca.es

Abstract

Two process to demarcate areas with analogous wind conditions have been developed in this analysis. The used techniques are based on clustering algorithms that will show us the wind directions relations for all stations placed in the studied zone. These relations will be used to build two matrixes, one for each method, allowing us working simultaneously with all relations. By permutation of elements on these matrixes it is possible to group related stations. These grouped distributions matrixes will be compared among themselves and with the wind directions correlation matrix to select the best algorithm of them.

Keywords: Cluster Analysis Clustering Applications Data Mining Self-Organizing Feature Map

Published: 2012-10-08

: http://dx.doi.org/10.1007/978-3-642-32304-1_2