The application of self-organizing methods in kohonen network for prediction of the profiles of load in a small power system
Tomasz Ciechulski , Stanisław Osowski
The paper shows the application of self-organizing methods in Kohonen network for prediction of the profiles of load in a small power system in Poland. Four learning methods were used: WTA, CWTA, Gaussian WTM and neural gas. The prediction of power consumption has been limited to the profile of load. The vector profile prognosis is equal to the average of vectors of the winning neurons in the appropriate days of the week and month.
|Journal series||Przegląd Elektrotechniczny, ISSN 0033-2097|
|Publication size in sheets||0.5|
|Score|| = 14.0, 29-06-2020, ArticleFromJournal|
= 14.0, 29-06-2020, ArticleFromJournal
|Publication indicators||= 1; : 2016 = 0.453; : 2013 = 0.0 (2)|
* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.