Probabilistic electricity price forecasting with Bayesian stochastic volatility models

Highlights: • The Bayesian approach is applied in order to forecast day-ahead electricity prices for the JCPL zone of the PJM Interconnection. • The results of Bayesian and non-Bayesian interval predictions are compared. In many cases the Bayesian predictions turn out superior. • The stochastic volatility model with a double exponential distribution of jumps, a leverage effect and exogenous variables is better than other models considered in the study. -- Abstract: The study is focused on probabilistic forecasts of day-ahead electricity prices. The Bayesian approach allows for conducting statistical inference about model parameters, latent volatility, jump times and their sizes. Moreover, the Bayesian forecasting takes into account uncertainty of parameter estimation. Using the PJM data sets we demonstrate that Bayesian stochastic volatility model with double exponential distribution of jumps and exogenous variables outperforms the non-Bayesian individual autoregressive models as well as three averaging schemes of spot price forecasts. We argue that the structure is a promising tool of modelling and forecasting electricity prices.