Assessment of the accuracy of electricity price forecasts on the basis of a mixed deterministic-probabilistic approach

Nowadays it is essential for an electricity market player to have not only tools for price forecasting, but also methods for quantifying the accuracy of such forecasts, in order to perform an optimum risk management of his physical/financial portfolio. This paper proposes a simple method to assess the accuracy of electricity price forecasts, based on the probability distributions of the main factors affecting the price. In particular, the method consists in the identification of the main drivers of the electricity spot price, the estimation of their probability distributions and finally their combination in order to determine the probability distribution of the corresponding electricity price. The sensitivity analysis between the price and its drivers is carried out by means of a deterministic electricity market simulator. The validity of the proposed methodology has been tested on the present scenario of the Italian electricity market (year 2004).