Title :
Data analysis by means of Kohonen feature maps for load forecast in power systems
Author :
Heine, Steffen ; Neumann, I.
Author_Institution :
Tech. Hochschule Leipzig, Germany
Abstract :
Because of the clustering and dimensionality reduction abilities the Kohonen feature map (KFM) can be the preferable tool for deriving knowledge about dependencies of the load consumption in electrical energy systems (EES). This paper describes the application of the KFM for analysing and splitting extensive load databases. The objective is to get separate clusters of load shapes for making short term load forecast (STLF) models with a high accuracy. The building of the forecast models is based on feedforward neural networks (NN)
Keywords :
data analysis; feedforward neural nets; load forecasting; self-organising feature maps; Kohonen feature maps; clustering; data analysis; dimensionality reduction abilities; electrical energy systems; feedforward neural networks; high accuracy; load consumption; load forecast; load shapes; power systems; short term forecast;
Conference_Titel :
Advances in Neural Networks for Control and Systems, IEE Colloquium on
Conference_Location :
Berlin
