Abstract
The forecast of carbon trading price is crucial to both sellers and purchasers; multi-scale integration models have been used widely in this process. However, these multi-scale models ignore the feature reconstruction process as well as the residual part and also they often focus on the linear integration. Meanwhile, most of the models cannot provide prediction interval which means they neglect the uncertainty. In this paper, an improved multi-scale nonlinear integration model is proposed. The original dataset is divided into some subgroups through variational mode decomposition (VMD) and all the subgroups will go through sample entropy (SE) process to reconstruct the features. Then, random forest and long-short term memory (LSTM) integration are used to model feature sub-sequences. For the residual part, LSTM residual correction strategy based on white noise test corrects residuals to obtain point prediction results. Finally, Gaussian process (GP) is applied to get the prediction interval estimate. The result shows that compared with some other methods, the proposed method can obtain satisfying accuracy which has the minimum statistical error. So, it is safe to conclude that the proposed method is able to efficiently predict the carbon price as well as to provide the prediction interval estimate.
Highlights
The global warming has posed a challenge to the world, and many countries as well as regions have begun to adopt the carbon emission trading approaches to effectively control greenhouse gas emissions [1] in an effort to reach the 26–28% target required by the 2030Paris Agreement [2]
The following main methods applied by the proposed model will be introduced: variational mode decomposition (VMD), random forest, long-short term memory (LSTM), and Gaussian process (GP)
The smaller the values of mean absolute error (MAE), RMSE, large, which will reduce certainty; or too small, which will lose the significance of interval
Summary
The global warming has posed a challenge to the world, and many countries as well as regions have begun to adopt the carbon emission trading approaches to effectively control greenhouse gas emissions [1] in an effort to reach the 26–28% target required by the 2030Paris Agreement [2]. China, known as the world second largest economy and the largest developing country, has become the biggest carbon emitter in the world, to cope with this situation, China has proposed a 60–65% reduction target in CO2 emissions from 2005 levels by 2030 [3]. China established a national emission trading system (ETS) to peak its carbon emission around 2030, building on the experience of pilot ETSs that are planned to be linked [4]. China has implemented a tradable green certificate market on the basis of the carbon emissions trading market [5]. The fundamental purpose of building a carbon emission trading market is to correct market failures and better play the decisive role of the market in the allocation of climate capacity resources. Through the development of the carbon market, our country has formed a carbon price mechanism covering key industries, and has transmitted it through the market to provide the market with long-term stable carbon price expectations, thereby influencing the investment and consumer behavior decisions of stakeholders, and promoting the transformation of country’s green and low-carbon development
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
