A game-theoretic model for electricity markets with tight capacity constraints

In this paper, an artificial neural network model for short-term price forecasting and a linear regression model for mid/long-term price forecasting are described together with forecasting results. A detailed discussion on the choice of forecast models and forecast variables is reported. The suggested methods are being utilized by the transmission company to forecast short-term and mid/long-term prices in the Zhejiang Electricity Market. The results show that the proposed forecast models meet the basic requirement of Zhejiang electricity market operation. A second objective of this work is to present the results of a series of experiments designed to justify certain game-theoretic assertions and to explain the price volatility experienced in many real-world markets under uniform pricing and pay-as-bid pricing. (C) 2007 Elsevier Ltd. All rights reserved.