A risk analysis method for carbon price prediction with hybrid intelligent model in consideration of variable selection of graphical modeling

This paper proposes a new risk assessment method for short-term carbon price prediction model. In this paper, a hybrid intelligent method of DA clustering and artificial neural network (ANN) is presented as a predictor of short-term carbon price. DA clustering plays a key role to classify input data into clusters. ANN is useful for predicting one-step ahead carbon price at each cluster. Graphical modeling is used to select meaningful input variables and provide more realistic relationship between input and output variables in the prediction model. To evaluate the uncertainty of the day-ahead carbon low, Monte-Carol simulation is carried out to generate sufficient realistic pseudo-scenarios with the multivariate normal random number. The proposed method is successfully applied to the real market data.