A Finite Mixture GARCH Approach with EM Algorithm for Energy Forecasting Applications

Enhancing forecasting performance in terms of both the expected mean value and variance has been a critical challenging issue for energy industry. In this paper, novel methodology finite mixture Generalized AutoRegressive Conditional Heteroskedasticity (GARCH) approach with Expectation–Maximization (EM) algorithm is introduced. The applicability comprehensively evaluated related time series including wind speed, power generation, electricity price. Its performances are by various criteria, also compared those conventional Moving-Average (ARMA) model less ARMA-GARCH model. It found that proposed GARCH outperforms other two models volatility modeling all considered. This proven to be statistically significant because p-values likelihood ratio test than 0.0001. On hand, estimations output, price, no improvement from obtained. results indicate viable mitigating associated risk predictions thanks reduced errors on modeling.