Input variable selection for ANN-based short-term load forecasting

Author

Drezga, I. ; Rahman, S.

Author_Institution

Center for Energy & the Global Environ., Virginia Polytech. Inst. & State Univ., Blacksburg, VA, USA

Volume

13

Issue

4

fYear

1998

fDate

11/1/1998 12:00:00 AM

Firstpage

1238

Lastpage

1244

Abstract

This paper describes a novel method for input variable selection for artificial neural network (ANN) based short-term load forecasting (STLF). The method is based on the phase-space embedding of a load time-series. The accuracy of the method is enhanced by the addition of temperature and cycle variables. To test the viability of the method, real load data for two US-based electric utilities were used. Only 15 input variables were identified in both cases and used for 24-hour ahead load forecasting. Results compare favorably to the ones reported in the literature, indicating that more parsimonious set of input variables can be used in STLF without sacrificing the accuracy of the forecast. This allows more compact ANNs, smaller training sets and easier training. Consequently, the method represents a step forward in determining a general procedure for input variable selection for ANN-based STLF

Keywords

learning (artificial intelligence); load forecasting; neural nets; power system analysis computing; time series; artificial neural network; computer simulation; electric utilities; input variable selection; load time-series; phase-space embedding; power systems; short-term load forecasting; training data; Artificial neural networks; Economic forecasting; Electronic mail; Input variables; Load forecasting; Power generation economics; Power system analysis computing; Power system economics; Temperature; USA Councils;

fLanguage

English

Journal_Title

Power Systems, IEEE Transactions on

Publisher

ieee

ISSN

0885-8950

Type

jour

DOI

10.1109/59.736244

Filename

736244