Hourly Electricity Price Forecasting Approach Based ARMA-GARCH Model

In power markets,accurate electricity price forecasting can help all market participants make optimal bidding or purchasing decisions and maximize their proceeds. Based on the analysis for the electricity price characteristic and impact factors,the power market patterns of China and the modeling process of ARMA-GARCH model are analyzed in detail.The ARMA-GARCH model can be established upon the Conditional Heteroskedasticity of the electricity price series.As per the time difference of the electricity price,the paper brings forward an idea that the constant days shall be divided into working days and weekends.Then the ARMA-GARCH models on them are established respectively.The results of PJM electric market show the effectiveness of the proposed methodology,which improves the accuracy of forecasting significantly. Due to the shortage of historic electricity price date and the nonstandard regulations of the power markets,the combined-forecasting method is given.