Modeling and short-term forecasting of the electricity price based on fuzzy Box-Jenkins

Any single one of the Auto-Regressive (AR) model, Moving Average (MA) model and Auto-Regressive and Moving Average (ARMA) model can not match the complex time-series data of electricity price, consequently the traditional Box-Jenkins method can not solve the forecasting of electricity price well. In this paper, fuzzy Box-Jenkins approach for modeling and short-term forecasting of the electricity price is proposed. A fuzzy strategy is introduced to determine the fuzzy factors corresponding to the AR, MA and ARMA models of Box-Jenkins method and further integrate the three models into a unified one through the fuzzy factors. The prediction of electricity price of Zhejiang power market shows that the fuzzy Box-Jenkins method can achieve better performance.