Summary:
In the context of competitive electricity markets, medium-term price forecasting plays an essential role for market stakeholders. In contrast to short-term price forecasting, very little research has been conducted in this field. Previous works regarding electricity price forecasting have tackled with theproblem of mid-term prediction by using fundamental market equilibrium models over daily or, at most, averages of groups of hours. On the other hand, the limitations of point forecasts are widely recognized and the literature dealing with probabilistic forecasts is scarce. In this study, a novel methodology to deal with medium-term hourly forecasting of electricity prices is proposed. This methodology is unique in the sense that it also attempts to simultaneously perform punctual and probabilistic hourly predictions. The approach consists of a nested combination of several modeling stages. The first stageconsists in the generation of multiple scenarios of uncertain variables. In a second stage, a market equilibrium model which incorporates Monte Carlo simulation and a new definition of load levels isexecuted for a reduced combination of the generated scenarios. The application of spatial interpolation techniques allows us to estimate numerous feasible realizations of electricity prices from only several hundreds executions of the fundamental market equilibrium model without losing accuracy. The eficiency of the proposed methodology is verified in a real-size electricity system characterized by a complex price dynamics: the Spanish market.
Keywords: Electricity prices, medium-term probabilistic forecasting, medium-term hourly prediction, Monte Carlo simulation
JCR Impact Factor and WoS quartile: Q1 (2016); 6,900 - Q1 (2023)
DOI reference: https://doi.org/10.1016/j.ijforecast.2015.06.002
Published on paper: September 2016.
Published on-line: September 2015.
Citation:
A. Bello, J. Reneses, A. Muñoz, A.R. Delgadillo, Probabilistic forecasting of hourly electricity prices in the medium-term using spatial interpolation techniques. International Journal of Forecasting. Vol. 32, nº. 3, pp. 966 - 980, September 2016. [Online: September 2015]