Short-term demand and energy price forecasting

Author

Contreras, Javier ; Santos, Jesus Riquelme

Author_Institution

ETS de Ingenieros Industriales, Castilla Univ.

fYear

2006

fDate

16-19 May 2006

Firstpage

924

Lastpage

927

Abstract

This paper is devoted to describe several forecasting techniques to predict market prices and demands in day-ahead electric energy markets. Price forecasting is performed using time series procedures, such as ARIMA, dynamic regression and transfer function methodologies. Demand forecasting is performed using time series procedures, artificial intelligence and combinations of several methods. Relevant conclusions are drawn on the effectiveness and flexibility of the considered techniques

Keywords

artificial intelligence; load forecasting; power engineering computing; power markets; pricing; time series; ARIMA; artificial intelligence; day-ahead electric energy markets; demand forecasting; dynamic regression; energy price forecasting; market prices; short-term demand; time series; transfer function methodologies; Artificial neural networks; Contracts; Demand forecasting; Economic forecasting; Electricity supply industry; Load forecasting; Power system modeling; Production; Time series analysis; Transfer functions; ANN; Electricity markets; demand forecasting; fuzzy logic; price forecasting; time series analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrotechnical Conference, 2006. MELECON 2006. IEEE Mediterranean

Conference_Location

Malaga

Print_ISBN

1-4244-0087-2

Type

conf

DOI

10.1109/MELCON.2006.1653249

Filename

1653249