Application of Computation Intelligence Techniques for Energy Load and Price Forecast in some States of USA

Author

Mourão, João C. ; Ruano, António E.

Author_Institution

Algarve Univ., Faro

fYear

2007

fDate

3-5 Oct. 2007

Firstpage

1

Lastpage

6

Abstract

The purpose of this paper is to forecast the load and the price of electricity, 49 hours ahead. To accomplish these goals, computational intelligence techniques were used, specifically artificial neural networks and genetic algorithms. The neural networks employed are RBFs (radial basis functions), fully connected and with just one hidden layer. The genetic algorithm used was MOGA (multiple objective genetic algorithm), which, as the name indicates, minimizes not a single objective but several. The neural networks are trained for one step ahead, and its output is feedback until 49 hours are calculated. MOGA is used for the input selection and for topology determination. The data used was kindly given by the University of Auburn, USA, and refers to real data from some North-American states.

Keywords

genetic algorithms; load forecasting; power system analysis computing; power system economics; pricing; radial basis function networks; USA; artificial neural network; computation intelligence technique; energy load forecasting; multiple objective genetic algorithm; price forecasting; radial basis function; Artificial neural networks; Competitive intelligence; Computational and artificial intelligence; Computational intelligence; Computer applications; Genetic algorithms; Load forecasting; Network topology; Neurofeedback; Output feedback; Load and price forecast; genetic algorithms; neural networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Signal Processing, 2007. WISP 2007. IEEE International Symposium on

Conference_Location

Alcala de Henares

Print_ISBN

978-1-4244-0829-0

Electronic_ISBN

978-1-4244-0830-6

Type

conf

DOI

10.1109/WISP.2007.4447559

Filename

4447559