Dynamic fuzzy estimation of contracts historic information using an automatic clustering methodology

Abstract

With the recent liberalization of electricity markets, market players need to decide whether to and how to participate in each electricity market type that is available to them. The search for the best opportunities to sell or buy the required energy is, however, not an easy task. Moreover, the changes that electricity markets are constantly suffering make this an highly dynamic environment, with huge associated unpredictability. Decision support tools become, therefore, essential for market players to be able to take the best advantage from market participation. This paper proposes a methodology to estimate the expected prices of bilateral contracts based on the analysis of contracts’ historic log. The proposed method is based on the application of a clustering methodology that groups the historic contracts according to their prices’ similarity. The optimal number of groups is automatically calculated taking into account the preference for the balance between the estimation error and the number of groups. The centroids of each cluster are used to define a dynamic fuzzy variable that approximates the tendency of contracts’ history. The resulting fuzzy variable allows estimating expected prices for contracts instantaneously and approximating missing values in the historic contracts log.