Applying ARMA-GARCH approaches to forecasting short-term electricity prices

Accurately modeling and predicting the mean and volatility of electricity prices can be of great importance to value electricity, bid or hedge against the volatility of electricity prices and manage risk. The paper applies various autoregressive moving average (ARMA) models with generalized autoregressive conditional heteroskedasticity (GARCH) processes, namely ARMA-GARCH models, along with their modified forms, ARMA-GARCH-in-mean (ARMA-GARCH-M), to model and forecast hourly ahead electricity prices. In total, 10 different model structures are adopted, and this paper thus conducts a comprehensive investigation on the ARMA-GARCH based time series forecasting of electricity prices. Multiple statistical measures are employed to evaluate the modeling sufficiency and predication accuracy of the ARMA-GARCH(-M) methods. The results show that the ARMA-GARCH-M models are in general an effective tool for modeling and forecasting the mean and volatility of electricity prices, while ARMA-SGARCH-M models are simple and robust and the ARMA-GJRGARCH-M model is very competitive. In addition, we observe that hourly electricity prices exhibit apparent daily, weekly and monthly periodicities, and have the nonlinear and asymmetric time-varying volatility together with an inverse leverage effect.

► Apply 10 ARMA-GARCH(-M) models to forecast electricity prices. ► Show that ARMA-GARCH-M models are more effective for forecasting price mean and volatility. ► Find that ARMA-SGARCH-M models are robust and ARMA-GJRGARCH-M models are competitive. ► Illustrate that hourly electricity prices exhibit daily, weekly and monthly periodicities. ► Disclose that prices have the nonlinear and asymmetric volatility with inverse leverage effect.