A Carbon Price Prediction Model Based on the Secondary Decomposition Algorithm and Influencing Factors

Carbon emission reduction is now a global issue, and the prediction of carbon trading market prices an important means reducing emissions. This paper innovatively proposes second decomposition price model based on nuclear extreme learning machine optimized by Sparrow search algorithm considers structural nonstructural influencing factors in model. Firstly, empirical mode (EMD) used to decompose data variational (VMD) Intrinsic Mode Function 1 (IMF1), as part input Then, maximum correlation minimum redundancy (mRMR) preprocess another After (SSA) optimizes relevant parameters Extreme Learning Machine with Kernel (KELM), for prediction. Finally, study, this selects two typical markets China analysis. In Guangdong Hubei markets, EMD-VMD-SSA-KELM superior other models. It shows that has good robustness validity.