12th International Conference on Probabilistic Methods Applied to Power Systems - PMAPS 2012, Estambul (Turquía). 10-14 junio 2012
Resumen:
This paper proposes a novel methodology to identify the appearance of extremely low electricity prices. This methodology is applied to the Spanish market, which has experienced a large number of hours with null price in recent times. The procedure is based on the statistical identification of the key drivers which are responsible to define the process. A first empirical analysis shows that unexpected low prices are caused by the recently increasing deployment of non-dispatchable generation which collapses thermal demand at certain moments. Decision trees and logistic regression techniques are used.We give a comprehensive theoretical proof of the proposed methodology, which empirically demonstrates its effectiveness by achieving promising experiment results on real market price data set. Both techniques are compared in terms of the results obtained. Examination of the models goodness of fit and interpretability is done by means of statistical and graphical tools. This theory to predict abnormal low prices can provide valuable information for companies when facing their decision making and riskmanagement process.
Palabras clave: Spanish electricity prices, extremely low prices, logistic regression, decision trees
Fecha de publicación: 2012-06-10.
Cita:
A. Bello, J. Reneses, J. Barquín, Forecasting of extremely low prices in the spanish electricity market: a logistic regression and decision-tree approach, 12th International Conference on Probabilistic Methods Applied to Power Systems - PMAPS 2012, Estambul (Turquía). 10-14 junio 2012.
