Analysis and models of electricity prices in the Italian ancillary services market

In this paper a time series approach is proposed for the analysis of electricity prices in the Italian ancillary services market. The objective is to forecast energy prices for lead times ranging from one hour to one day. Both black-box and grey-box multivariate models are adopted for the analysis of the conditional mean values of the price series. Real data regarding a geographical zone of the Italian electricity system are processed, showing that the adopted models allow for a significant reduction of the prediction error variance with respect to that of standard naive predictors.