We propose and study a new model for the description and the forecast of the gross prices of electricity in the liberalized Italian energy market via an additive two-factor model. Among the characteristics of the spot prices, it is shown a presence of self-correlations in the price increments. Furthermore, it is interesting to notice that in the case of the Italian electricity market the presence of several jumps is shown, many of which appearing clustered over short time periods. Hence, the two-factor model we propose is driven by both a Hawkes and a fractional Brownian processes. We examine the system into the details from a modelling point of view; then, we perform a calibration procedure by discussing the seasonality, the identification of the spikes and the estimate of the Hurst coefficient. After the calibration and the validation of the model, we consider its forecasting performance via a class of adequate evaluation metrics.
A fractional Brownian - Hawkes model for the Italian electricity spot market: estimation and forecasting / L. Giordano, D. Morale. - (2019 Nov 26).
|Titolo:||A fractional Brownian - Hawkes model for the Italian electricity spot market: estimation and forecasting|
MORALE, DANIELA (Corresponding)
|Parole Chiave:||Energy markets, Hawkes model, fractional Brownian motion, stochastic modelling and forecasting, Italian spot prices|
|Settore Scientifico Disciplinare:||Settore MAT/06 - Probabilita' e Statistica Matematica|
|Data di pubblicazione:||2019-11-26|
|Appare nelle tipologie:||24 - Pre-print|
File in questo prodotto:
|GIORDANO_MORALE_modeling_forecasting_ electricity_prices_air.pdf||Post-print, accepted manuscript ecc. (versione accettata dall'editore)||Administrator Richiedi una copia|
|1911.11795.pdf||Pre-print (manoscritto inviato all'editore)||Open Access Visualizza/Apri|