Research on Carbon Price Volatility Prediction Based on CEEMDAN and Optimized LSTM Model

• 1、 School of Mathematics and Physics，North China Electric Power University，Beijing 102206

Abstract：Excessive carbon dioxide emissions have become a serious challenge facing the current society. Establishing a carbon emissions trading market can effectively reduce social carbon emissions and promote green economic transformation. The Chinese government proposed the goals of carbon peaking and carbon neutrality in 2020, and the construction of the domestic carbon market is currently in the stage of developing a unified national carbon market. Enriching research on carbon price volatility is of great significance for establishing a reasonable pricing mechanism and carbon quota allocation system. This paper takes the realized volatility of Beijing carbon emission allowance trading prices as the research object, constructs a hybrid forecasting model based on complete ensemble empirical mode decomposition with adaptive noise and long short-term memory network, and optimizes the model structural parameters through particle swarm optimization algorithm. The experimental results demonstrate that the model has the advantages of extracting multi-scale complex time series volatility trends and effectively processing financial time series. The particle swarm optimization algorithm optimizes the structural parameters of the forecasting model to avoid fitting problems caused by improper parameter selection. The model has significant accuracy and stability in forecasting carbon price volatility.

Keywords： Carbon price；Realized volatility；Complete ensemble empirical mode decomposition with adaptive noise；Long short-term memory networks；Particle swarm optimization algorithm；Time series forecasting