Abstract
Carbon price is closely related to energy conservation and emission reduction cost, and carbon price forecasting is conducive to improving and stabilizing market trading mechanisms. Considering the matching relationship between the prediction model and the carbon price market, a decomposition ensemble carbon price forecasting method based on reinforcement learning model fusion is designed. Firstly, considering the problem of disharmony between different base models and data patterns, a model matching strategy is developed to match the appropriate prediction base model for each carbon trading market. Secondly, the empirical wavelet transform (EWT) algorithm is used to decompose the carbon price into several subseries, which reduces the complexity of the original data and improves the prediction effect of each base model. Finally, for each carbon price market, the Q-learning algorithm of reinforcement learning is used to integrate the prediction results of the selected multiple base models into the final price forecasting of the corresponding market. The model is verified in the seven carbon trading markets, and experiments show that the model has superior and stable prediction performance compared with other methods. The mean absolute percentage errors of the Hubei, Beijing, Shenzhen, Chongqing, Tianjin, Shanghai, and EU markets are only 0.3515%, 1.2335%, 1.3388%, 1.2128%, 0.3229%, 0.2418%, and 0.4094%, respectively. It shows that the EWT method and reinforcement learning ensemble strategy do improve the prediction performance, and the proposed model can be used as a feasible tool for price assessment and management in carbon price markets.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availability
All study data sources were authentic and reliable.
Abbreviations
- AFSA:
-
Artificial fish swarm algorithm
- APSO:
-
Adaptive particle swarm optimization
- ARIMA:
-
Auto-regressive integrated moving average
- BiGRU:
-
Bidirectional gated recurrent unit
- BiLSTM:
-
Bidirectional long short-term memory
- BPNN:
-
Back propagation neural network
- CEEMD:
-
Complementary ensemble empirical mode decomposition
- CEEMDAN:
-
Complete ensemble empirical mode decomposition with adaptive noise
- DA:
-
Direction accuracy
- DBN:
-
Deep belief network
- DE:
-
Differential evolution
- ELM:
-
Extreme learning machine
- EMD:
-
Empirical mode decomposition
- ENN:
-
Elman neural network
- ESN:
-
Echo state network
- EU:
-
European Union
- EUA:
-
European Union allowance
- EWT:
-
Empirical wavelet transform
- GA:
-
Genetic algorithm
- GARCH:
-
Generalized auto-regressive conditional heteroskedasticity
- GBDT:
-
Gradient boosting decision tree
- GWO:
-
Grey wolf optimization
- ICA:
-
Imperial competition algorithm
- ICAP:
-
International Carbon Action Partnership
- ICEEMDAN:
-
Improved complementary ensemble empirical mode decomposition with adaptive noise
- ISSA:
-
Improved sparrow search algorithm
- KELM:
-
Kernel extreme learning machine
- LSSVM:
-
Least square support vector machine
- LSTM:
-
Long short-term memory
- MAE:
-
Mean absolute error
- MAPE:
-
Mean absolute percentage error
- MDA:
-
Modified direction accuracy
- MLP:
-
Multi-layer perceptron
- MMAdapGA:
-
Multiple mutations adaptive genetic algorithm
- ORELM:
-
Outlier-robust extreme learning machine
- PE:
-
Permutation entropy
- PSO:
-
Particle swarm optimization
- RMSE:
-
Root mean square error
- RNN:
-
Recursive neural network
- RVM:
-
Relevance vector machine
- SA:
-
Simulated annealing
- SE:
-
Sample entropy
- SVR:
-
Support vector regression
- TCN:
-
Temporal convolutional network
- VAR:
-
Vector auto-regressive
- VMD:
-
Variational mode decomposition
References
Chen P, Vivian A, Ye C (2022) Forecasting carbon futures price: a hybrid method incorporating fuzzy entropy and extreme learning machine. Ann Oper Res 313(1):559–601. https://doi.org/10.1007/s10479-021-04406-4
Cheng Z, Zhao Q, Wang F, Jiang Y, Xia L, Ding J (2016) Satisfaction based Q-learning for integrated lighting and blind control. Energy and Buildings 127:43–55. https://doi.org/10.1016/j.enbuild.2016.05.067
Cheng YH, Hu BB (2022) Forecasting regional carbon prices in China based on secondary decomposition and a hybrid kernel-based extreme learning machine. Energies 15 (10). https://doi.org/10.3390/en15103562
Chun D, Cho H, Kim J (2022) The relationship between carbon-intensive fuel and renewable energy stock prices under the emissions trading system. Energy Econ 114:106257. https://doi.org/10.1016/j.eneco.2022.106257
Dong HM, Liu YS, Zhao ZH, Tan XJ, Managi S (2022) Carbon neutrality commitment for China: from vision to action. Sustain Sci 17(5):1741–1755. https://doi.org/10.1007/s11625-022-01094-2
Eğrioğlu E, Aladağ ÇH, Günay S (2008) A new model selection strategy in artificial neural networks. Appl Math Comput 195(2):591–597. https://doi.org/10.1016/j.amc.2007.05.005
Gilles J (2013) Empirical wavelet transform. IEEE Trans Signal Process 61(16):3999–4010. https://doi.org/10.1109/TSP.2013.2265222
Han M, Ding L, Zhao X, Kang W (2019) Forecasting carbon prices in the Shenzhen market, China: the role of mixed-frequency factors. Energy 171:69–76. https://doi.org/10.1016/j.energy.2019.01.009
Hao Y, Tian C (2020) A hybrid framework for carbon trading price forecasting: The role of multiple influence factor. J Clean Prod 262:120378. https://doi.org/10.1016/j.jclepro.2020.120378
Hu M, Wang G, Ma K, Cao Z, Yang S (2021) Bearing performance degradation assessment based on optimized EWT and CNN. Measurement 172. https://doi.org/10.1016/j.measurement.2020.108868
Huang Z, Dong H, Jia S (2022) Equilibrium pricing for carbon emission in response to the target of carbon emission peaking. Energy Econ 112:106160. https://doi.org/10.1016/j.eneco.2022.106160
Ji Q, Zhang D, Geng J-b (2018) Information linkage, dynamic spillovers in prices and volatility between the carbon and energy markets. J Clean Prod 198:972–978. https://doi.org/10.1016/j.jclepro.2018.07.126
Kong Y, Wang T, Chu F (2019) Meshing frequency modulation assisted empirical wavelet transform for fault diagnosis of wind turbine planetary ring gear. Renew Energy 132:1373–1388. https://doi.org/10.1016/j.renene.2018.09.027
Li YM, Song JW (2022) Research on the application of GAELM model in carbon trading price an example of Beijing. Polish J Environ Stud 31(1):149–161. https://doi.org/10.15244/pjoes/138357
Lin Y, Lu Q, Tan B, Yu YY (2022) Forecasting energy prices using a novel hybrid model with variational mode decomposition. Energy 246. https://doi.org/10.1016/j.energy.2022.123366
Liu H, Yu C, Wu H, Duan Z, Yan G (2020) A new hybrid ensemble deep reinforcement learning model for wind speed short term forecasting. Energy 202:117794. https://doi.org/10.1016/j.energy.2020.117794
Liu H, Yang R, Wang T, Zhang L (2021a) A hybrid neural network model for short-term wind speed forecasting based on decomposition, multi-learner ensemble, and adaptive multiple error corrections. Renew Energy 165:573–594. https://doi.org/10.1016/j.renene.2020.11.002
Liu Z, Jiang P, Wang J, Zhang L (2021b) Ensemble forecasting system for short-term wind speed forecasting based on optimal sub-model selection and multi-objective version of mayfly optimization algorithm. Expert Systems with Applications 177. https://doi.org/10.1016/j.eswa.2021.114974
Liu JP, Wang PA, Chen HY, Zhu JM (2022a) A combination forecasting model based on hybrid interval multi-scale decomposition: application to interval-valued carbon price forecasting. Expert Systems With Applications 191. https://doi.org/10.1016/j.eswa.2021.116267
Liu Q, Liu M, Zhou H, Yan F (2022b) A multi-model fusion based non-ferrous metal price forecasting. Resources Policy 77. https://doi.org/10.1016/j.resourpol.2022.102714
Mughees N, Mohsin SA, Mughees A, Mughees A (2021) Deep sequence to sequence Bi-LSTM neural networks for day-ahead peak load forecasting. Expert Syst Appl 175:114844. https://doi.org/10.1016/j.eswa.2021.114844
Niu X, Wang J, Wei D, Zhang L (2022) A combined forecasting framework including point prediction and interval prediction for carbon emission trading prices. Renew Energy. https://doi.org/10.1016/j.renene.2022.10.027
Qi S, Cheng S, Tan X, Feng S, Zhou Q (2022) Predicting China’s carbon price based on a multi-scale integrated model. Appl Energy 324:119784. https://doi.org/10.1016/j.apenergy.2022.119784
Šemrov D, Marsetič R, Žura M, Todorovski L, Srdic A (2016) Reinforcement learning approach for train rescheduling on a single-track railway. Transport Res Part B: Methodol 86:250–267. https://doi.org/10.1016/j.trb.2016.01.004
Sun W, Huang C (2020) A carbon price prediction model based on secondary decomposition algorithm and optimized back propagation neural network. J Clean Prod 243:118671. https://doi.org/10.1016/j.jclepro.2019.118671
Sun W, Zhang J (2022) A novel carbon price prediction model based on optimized least square support vector machine combining characteristic-scale decomposition and phase space reconstruction. Energy 253:124167. https://doi.org/10.1016/j.energy.2022.124167
Sun S, Jin F, Li H, Li Y (2021) A new hybrid optimization ensemble learning approach for carbon price forecasting. Appl Math Model 97:182–205. https://doi.org/10.1016/j.apm.2021.03.020
Sun S, Wang Y, Meng Y, Wang C, Zhu X (2022) Multi-step wind speed forecasting model using a compound forecasting architecture and an improved QPSO-based synchronous optimization. Energy Rep 8:9899–9918. https://doi.org/10.1016/j.egyr.2022.07.164
Tian C, Hao Y (2020) Point and interval forecasting for carbon price based on an improved analysis-forecast system. Appl Math Model 79:126–144. https://doi.org/10.1016/j.apm.2019.10.022
Wang XP, Yan LN (2022) Measuring the integrated risk of Chinaʼs carbon financial market based on the copula model. Environ Sci Pollut Res 29(36):54108–54121. https://doi.org/10.1007/s11356-022-19679-w
Wang J, Cui Q, He M (2022a) Hybrid intelligent framework for carbon price prediction using improved variational mode decomposition and optimal extreme learning machine. Chaos Solitons Fractals 156:111783. https://doi.org/10.1016/j.chaos.2021.111783
Wang L, Wang Z, Ma Y (2022b) Does environmental regulation promote the high-quality development of manufacturing? A quasi-natural experiment based on China’s carbon emission trading pilot scheme. Socioecon Plann Sci 81:101216. https://doi.org/10.1016/j.seps.2021.101216
Wang P, Liu J, Tao Z, Chen H (2022c) A novel carbon price combination forecasting approach based on multi-source information fusion and hybrid multi-scale decomposition. Eng Appl Artif Intell 114:105172. https://doi.org/10.1016/j.engappai.2022.105172
Wang J, Wang Y, Li H, Yang H, Li Z (2023) Ensemble forecasting system based on decomposition-selection-optimization for point and interval carbon price prediction. Appl Math Model 113:262–286. https://doi.org/10.1016/j.apm.2022.09.004
Wang JJ, Cui Q, Sun X (2021) A novel framework for carbon price prediction using comprehensive feature screening, bidirectional gate recurrent unit and Gaussian process regression. J Clean Prod 314. https://doi.org/10.1016/j.jclepro.2021.128024
Wang X, Mao YQ, Duan YH, Guo YB (2022d) A Study on China coal Price forecasting based on CEEMDAN-GWO-CatBoost hybrid forecasting model under Carbon Neutral Target. Frontiers in Environmental Science 10. https://doi.org/10.3389/fenvs.2022.1014021
Yan W-L, Cheung A (2022) The dynamic spillover effects of climate policy uncertainty and coal price on carbon price: Evidence from China. Finance Res Lett 103400. https://doi.org/10.1016/j.frl.2022.103400
Yang H, Liu Z, Li G (2022) A new hybrid optimization prediction model for PM2.5 concentration considering other air pollutants and meteorological conditions. Chemosphere 307:135798. https://doi.org/10.1016/j.chemosphere.2022.135798
Yang P, Wang Y, Zhao S, Chen Z, Li Y (2022b) A carbon price hybrid forecasting model based on data multi-scale decomposition and machine learning. Environ Sci Pollut Res. https://doi.org/10.1007/s11356-022-22286-4
Yang W, Sun S, Hao Y, Wang S (2022c) A novel machine learning-based electricity price forecasting model based on optimal model selection strategy. Energy 238. https://doi.org/10.1016/j.energy.2021.121989
Zhang F, Wen N (2022) Carbon price forecasting: a novel deep learning approach. Environ Sci Pollut Res 29(36):54782–54795. https://doi.org/10.1007/s11356-022-19713-x
Zhang J, Li D, Hao Y, Tan Z (2018) A hybrid model using signal processing technology, econometric models and neural network for carbon spot price forecasting. J Clean Prod 204:958–964. https://doi.org/10.1016/j.jclepro.2018.09.071
Zhang C-X, Li J, Huang X-F, Zhang J-S, Huang H-C (2022) Forecasting stock volatility and value-at-risk based on temporal convolutional networks. Expert Syst Appl 207:117951. https://doi.org/10.1016/j.eswa.2022.117951
Zhang T, Tang Z, Wu J, Du X, Chen K (2021) Multi-step-ahead crude oil price forecasting based on two-layer decomposition technique and extreme learning machine optimized by the particle swarm optimization algorithm. Energy 229. https://doi.org/10.1016/j.energy.2021.120797
Zhou JG, Xu ZT, Wang SG (2022b) A novel hybrid learning paradigm with feature extraction for carbon price prediction based on Bi-directional long short-term memory network optimized by an improved sparrow search algorithm. Environ Sci Pollut Res 29(43):65585–65598. https://doi.org/10.1007/s11356-022-20450-4
Zhou FT, Huang ZH, Zhang CH (2022a) Carbon price forecasting based on CEEMDAN and LSTM. Applied Energy 311. https://doi.org/10.1016/j.apenergy.2022.118601
Zhu B, Wan C, Wang P (2022) Interval forecasting of carbon price: a novel multiscale ensemble forecasting approach. Energy Econ 106361. https://doi.org/10.1016/j.eneco.2022.106361
Funding
The study is fully supported by the National Natural Science Foundation of China (grant No. 52072412), the Changsha Science & Technology Project (grant No. KQ1707017), and the Hunan Province Science and Technology Talent Support Project (grant No. 2020TJ-Q06).
Author information
Authors and Affiliations
Contributions
Zijie Cao: writing—original draft, validation, software. Hui Liu: methodology, writing—original draft.
Corresponding author
Ethics declarations
Ethics approval
Not applicable.
Consent to participate
Not applicable.
Consent for publication
Not applicable.
Competing interests
The authors declare no competing interests.
Additional information
Responsible Editor: Philippe Garrigues
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Cao, Z., Liu, H. A novel carbon price forecasting method based on model matching, adaptive decomposition, and reinforcement learning ensemble strategy. Environ Sci Pollut Res 30, 36044–36067 (2023). https://doi.org/10.1007/s11356-022-24570-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11356-022-24570-9