STRUCTURAL TIME SERIES MODELS FOR LEVEL AND VOLATILITY OF HOURLY ELECTRICITY PRICES

This study considers an empirical investigation of the hourly PUN, which is the spot price of a megawatt on the Italian electricity market. This price is characterised by strong intra-day seasonality, i.e., hourly effects, which influence the level and volatility price, and many parameters are involved in the ARMA-GARCH modelling process. In order to reduce the number of parameters, an alternative modelling approach is presented based on structural time series modelling, i.e., an autoregressive model with seasonal effects at the PUN level and a stochastic volatility model (with seasonal effects) for the PUN volatility. This modelling approach allows us to treat seasonality as a latent stochastic component, which is governed by only a few parameters. The results obtained using this method demonstrate that the proposed modelling approach has beneficial strengths, and thus it should be developed further.