Stochastic model of residual demand curves with decision trees.

Abstract

Generating firms operating in deregulated markets need strategic bidding procedures to maximize their expected profits. In some electricity markets, due to the number and size of the participants, the clearing price may be affected by the production supplied to the market. To model this effect, the residual demand curve (RDC) is considered. This paper proposes a methodology based on decision trees to estimate the probabilistic RDC that a generating agent faces in each hourly period of the market. The method explains the behavior of the RDC patterns (obtained through clustering techniques) by a set of factors (linear combinations of explanatory variables) determined by the statistical technique factor analysis. A decision tree is built to compute the probability of each RDC pattern, taking as input estimations of the numerical value of the explanatory factors. In addition, the paper describes the stochastic programming formulation of the RDC patterns to obtain optimal bidding curves. The methodology proposed is illustrated with a case study applied to the first intradaily market of the Spanish electricity market.