Carbon Trading Price Prediction Based On Improved Multi-objective Grey Wolf Optimization Algotithm

With the development of science and technology,people are paying more and more attention to the impact of greenhouse gases on human beings.Scholars from various countries have taken action and proposed various measures to eliminate the negative effects of greenhouse gases.The carbon trading price market mechanism is one of the measures.Therefore,accurate prediction of carbon trading prices is of great significance for making emission reduction decisions.This thesis presents a “decomposition-integration” model,which integrates improved ensemble empirical mode decomposition(ICEEMD),improved multi-objective grey wolf optimization algorithm(IMOGWO),and extreme learning machine(ELM)to predict the carbon trading price.First,in this paper,ICEEMD is used to decompose the data that has processed the missing values and outliers,and a residual sequence(Redisual)and some intrinsic mode functions(IMFs)are obtained.Then the prediction method of this thesis select the extreme learning machine.Improved multi-objective grey wolf optimization algorithm is adopted to deal with the optimization of weights and thresholds in extreme learning machine.A“decomposition-integration” model(ICEEMD_IMOGWO_ELM)is finally obtained.In the analysis section at the end of this thesis,the carbon trading price data of Hubei and Shenzhen are selected for empirical analysis,and three single prediction models and seven mixed prediction models are compared with the models proposed in this thesis.The result shows that the model proposed in this paper not only has high prediction accuracy but also has good stability.