A SOM neural network approach to load forecasting. Meteorological and time frame influence

Author

López, M. ; Valero, S. ; Senabre, C. ; Aparicio, J.

Author_Institution

Dipt. de Ing. de Sist. Ind., Univ. Miguel Hernandez de Elche (UMH), Elche, Spain

fYear

2011

fDate

11-13 May 2011

Firstpage

1

Lastpage

5

Abstract

An artificial neural network based on Kohonen self-organizing maps (SOM) and its application to short-term load forecasting (STLF) is presented. The proposed model is capable of forecasting up to 24 hour long profiles, up to 24 hours ahead of the beginning of the period. The input used by the model depends on the available information at the time of the forecast, and it may contain meteorological variables and previous hourly load values. Also, different time frames for the input training data are analyzed. The output of the model is a curve of the forecasted load for the specified period. The test of forecasting 2009 data from the Spanish power system resulted in a 2.67% MAPE (mean absolute percentage error).

Keywords

load forecasting; self-organising feature maps; Kohonen self-organizing maps; SOM neural network; artificial neural network; forecasted load; mean absolute percentage error; short-term load forecasting; Forecasting; Load forecasting; Load modeling; Predictive models; Training; Training data; Weather forecasting;

fLanguage

English

Publisher

ieee

Conference_Titel

Power Engineering, Energy and Electrical Drives (POWERENG), 2011 International Conference on

Conference_Location

Malaga

ISSN

2155-5516

Print_ISBN

978-1-4244-9845-1

Electronic_ISBN

2155-5516

Type

conf

DOI

10.1109/PowerEng.2011.6036553

Filename

6036553