Matlab Application of Kohonen Self-organizing Map to Classify Consumers’ Load Profiles

This paper proposes a Matlab object oriented application based on Kohonen Self- Organizing Maps (SOM) able to classify consumers’ daily load profile. Firstly, the characteristics of Kohonen self- organizing maps are briefly described in order to underline the advantages and disadvantages of these ty...

Full description

Saved in:
Bibliographic Details
Published inProcedia computer science Vol. 31; pp. 474 - 479
Main Authors Dragomir, Otilia Elena, Dragomir, Florin, Radulescu, Marian
Format Journal Article
LanguageEnglish
Published Elsevier B.V 2014
Subjects
classification
decision support system
Kohonen
load
neural networks
Self- Organizing Map
load
classification
Kohonen
Self- Organizing Map
neural networks
decision support system
Online AccessGet full text

Cover

More Information
Summary:This paper proposes a Matlab object oriented application based on Kohonen Self- Organizing Maps (SOM) able to classify consumers’ daily load profile. Firstly, the characteristics of Kohonen self- organizing maps are briefly described in order to underline the advantages and disadvantages of these types of neural networks in classifications approaches. In the second part, data used for classification of load daily profiles is processed using statistical methods and Matlab. The result of these computations is a data base composed of daily load profiles used for SOM training. In the third part, the proposed software is tested on several scenarios in order to classify different consumers’ load profiles.
ISSN:1877-0509
1877-0509
DOI:10.1016/j.procs.2014.05.292