Hongkai Zhao, Nan Ye, Bowen Xia
Department of Economic Management, North China Electric Power University, Baoding, China
Carbon price prediction is of cardinal significance for promoting the development of carbon trading market. However, the strong non-stationary and nonlinearity characteristics of the carbon price pose a challenge to the carbon price prediction model. To improve the accuracy of carbon price prediction, a combined model based on ensemble empirical mode decomposition (EEMD) is proposed in this paper. In the proposed model, EEMD is used to decompose the original data into a series of relatively stable component sequences. Then, the extreme learning machine (ELM) and BP neural network (BP) optimized by particle swarm optimization algorithm (PSO) are used to respectively predict the component sequences and integrate the predicted results. Finally, the weights of the two prediction methods are determined by the variance-covariance method, and the final combined prediction result is obtained. To verify the performance of proposed model, the carbon price sequences of Shenzhen and Hubei of China were selected. The results showed that the combined model had good performance.
carbon price forecasting, ensemble empirical mode decomposition, he extreme learning machine, BP neural network, the combination forecasting method
Hongkai Zhao, Nan Ye, Bowen Xia. A Novel Hybrid Model Using EEMD and Neural Network for Forecasting Carbon Price. Academic Journal of Humanities & Social Sciences (2020) Vol. 3, Issue 5: 96-116. https://doi.org/10.25236/AJHSS.2020.030512.
 SHI Q, CHEN J, SHEN L. Driving factors of the changes in the carbon emissions in the Chinese construction industry[J]. Journal of Cleaner Production, 2017,166:615-627.
 SUN W, WANG C, ZHANG C. Factor analysis and forecasting of CO2 emissions in Hebei, using extreme learning machine based on particle swarm optimization[J]. Journal of Cleaner Production, 2017,162:1095-1101.
 ZHANG Y, WEI Y. An overview of current research on EU ETS: Evidence from its operating mechanism and economic effect[J]. Applied Energy, 2010,87(6):1804-1814.
 WENG Q, XU H. A review of China’s carbon trading market[J]. Renewable and Sustainable Energy Reviews, 2018,91:613-619.
 ZHU B, HAN D, WANG P, et al. Forecasting carbon price using empirical mode decomposition and evolutionary least squares support vector regression[J]. Applied Energy, 2017,191:521-530.
 HAN S K, AHN J J, OH K J, et al. A new methodology for carbon price forecasting in EU ETS[J]. Expert Systems, 2015,32(2):228-243.
 Quan C. Research on carbon price prediction based on ELM-VMD hybrid model[D]. 2018
 ZHANG J, LI D, HAO Y, et al. A hybrid model using signal processing technology, econometric models and neural network for carbon spot price forecasting[J]. Journal of Cleaner Production, 2018,204:958-964.
 ZHAO X, HAN M, DING L, et al. Usefulness of economic and energy data at different frequencies for carbon price forecasting in the EU ETS[J]. Applied Energy, 2018,216:132-141.
 Guan X. Research on carbon market trading price prediction based on grey theory[D]. 2016
 LI W, LU C. The research on setting a unified interval of carbon price benchmark in the national carbon trading market of China[J]. Applied Energy, 2015,155:728-739.
 Yao Y, Lv J, Zhang C. Carbon market price formation mechanism and price prediction in Hubei province[J]. Statistics and decision making, 2017(19):166-169.
 AROURI M E H, JAWADI F, NGUYEN D K. Nonlinearities in carbon spot-futures price relationships during Phase II of the EU ETS[J]. Economic Modelling, 2012,29(3):884-892.
 BYUN S J, CHO H. Forecasting carbon futures volatility using GARCH models with energy volatilities[J]. Energy Economics, 2013,40:207-221.
 Zhu B, Wei Y. Carbon price forecasting with a novel hybrid ARIMA and least squares support vector machines methodology. Omega. 2013;41:517-524.
 SUN W, HUANG C. A carbon price prediction model based on secondary decomposition algorithm and optimized back propagation neural network[J]. Journal of Cleaner Production, 2020,243:118671.
 SUN W, ZHANG C. Analysis and forecasting of the carbon price using multi—resolution singular value decomposition and extreme learning machine optimized by adaptive whale optimization algorithm[J]. Applied Energy, 2018,231:1354-1371.
 ZHU B. A novel multiscale ensemble carbon price prediction model integrating empirical mode decomposition, genetic algorithm and artificial neural network[J]. Energies, 2012,5(2):355-370.
 SUN G, CHEN T, WEI Z, et al. A carbon price forecasting model based on variational mode decomposition and spiking neural networks[J]. Energies, 2016,9(1):54.
 Zhaohua W U , Huang N E . Ensemble empirical mode decomposition: a noise-assisted data analysis method[J]. Advances in Adaptive Data Analysis, 2014, 01(01):0900004.
 ZHOU J, YU X, YUAN X. Predicting the carbon price sequence in the Shenzhen emissions exchange using a multiscale ensemble forecasting model based on ensemble empirical mode decomposition[J]. Energies, 2018,11(7):1907.
 Liu J, Guo Y, Chen H, et al. Multi-scale combinatorial prediction of carbon price based on popular learning of unstructured data[J]. Statistics and decision making, 2019,34(02):279-286.
 HUANG G, ZHU Q, SIEW C. Extreme learning machine: Theory and applications[J]. Neurocomputing, 2006,70(1-3):489-501.