Title :
A SOM-based hierarchical model to short-term load forecasting
Author :
Carpinteiro, Otávio A S ; Reis, Agnaldo J R
Author_Institution :
Fed. Univ. of Itajuba, Itajuba
Abstract :
This paper proposes a SOM-based hierarchical neural model to the problem of short-term load forecasting. The neural model is made up of two self-organizing map nets - one on top of the other. It has been successfully applied to domains which require time series analysis. The model was trained and assessed on load data extracted from a Brazilian electric utility. It was required to predict once every hour the electric load during the next 24 hours. The paper presents the results, and evaluates them.
Keywords :
load forecasting; power engineering computing; self-organising feature maps; Brazilian electric utility; SOM-based hierarchical model; load data extraction; neural model; self-organizing map nets; short-term load forecasting; Data mining; Load forecasting; Load modeling; Multilayer perceptrons; Neural networks; Power industry; Power system modeling; Power system security; Predictive models; Training data;
Conference_Titel :
Power Tech, 2005 IEEE Russia
Conference_Location :
St. Petersburg
Print_ISBN :
978-5-93208-034-4
Electronic_ISBN :
978-5-93208-034-4
DOI :
10.1109/PTC.2005.4524693
