Forecasting Carbon Trading in the Green Energy Economy Using Autoformer
DOI:
https://doi.org/10.54097/g6t9th07Keywords:
Carbon Price Forecasting; Green Energy; Time-Series Forecasting; Autoformer.Abstract
Amid the global energy transition and expanding carbon markets, accurately forecasting carbon emission allowance (CEA) prices is crucial for effective policymaking and risk management. Existing models struggle to capture the non-stationary dynamics of carbon prices, which are driven by external shocks and inherent multi-scale periodicities. To address this, we propose a multivariate forecasting framework based on Autoformer. By leveraging the superior nonlinear forecasting capabilities of Autoformer and constructing multi-dimensional input feature vectors, the proposed method effectively captures latent periodic patterns embedded in time series data of CEA. Rigorous empirical evaluations demonstrate that our method significantly outperforms baselines.
Downloads
References
[1] Brockhaus M, Obeng-Odoom F, Wong G, et al. The Forest-related finance landscape and potential for just investments[J]. International Forest Governance: A Critical Review of Trends, Drawbacks, and New Approaches. A Global Assessment Report, 2024: 57-81.
[2] Campiglio E. Beyond carbon pricing: The role of banking and monetary policy in financing the transition to a low-carbon economy[J]. Ecological economics, 2016, 121: 220-230.
[3] Lohmann L. Uncertainty markets and carbon markets: Variations on Polanyian themes[J]. New Political Economy, 2010, 15(2): 225-254.
[4] Dawes R M, Corrigan B. Linear models in decision making[J]. Psychological bulletin, 1974, 81(2): 95.
[5] Khan A, Rauf Z, Sohail A, et al. A survey of the vision transformers and their CNN-transformer based variants[J]. Artificial Intelligence Review, 2023, 56(Suppl 3): 2917-2970.
[6] Lucas Y, Portier P E, Laporte L, et al. Towards automated feature engineering for credit card fraud detection using multi-perspective HMMs[J]. Future Generation Computer Systems, 2020, 102: 393-402.
[7] Schaffer A L, Dobbins T A, Pearson S A. Interrupted time series analysis using autoregressive integrated moving average (ARIMA) models: a guide for evaluating large-scale health interventions[J]. BMC medical research methodology, 2021, 21(1): 58.
[8] Bollerslev T. Generalized autoregressive conditional heteroskedasticity[J]. Journal of econometrics, 1986, 31(3): 307-327.
[9] Schuster M, Paliwal K K. Bidirectional recurrent neural networks[J]. IEEE transactions on Signal Processing, 1997, 45(11): 2673-2681.
[10] Box G E P, Jenkins G M, Reinsel G C, et al. Time series analysis: forecasting and control[M]. John Wiley & Sons, 2015.
[11] Eck D, Schmidhuber J. Finding temporal structure in music: Blues improvisation with LSTM recurrent networks[C]//Proceedings of the 12th IEEE workshop on neural networks for signal processing. IEEE, 2002: 747-756.
[12] Nguyen V N, Tarełko W, Sharma P, et al. Potential of explainable artificial intelligence in advancing renewable energy: challenges and prospects[J]. Energy & Fuels, 2024, 38(3): 1692-1712.
[13] Qian X, Zhang C, Chen L, et al. Deep learning-based identification of maize leaf diseases is improved by an attention mechanism: Self-attention[J]. Frontiers in plant science, 2022, 13: 864486.
[14] Li S, Zhao Y, Varma R, et al. Pytorch distributed: Experiences on accelerating data parallel training[J]. arXiv preprint arXiv:2006.15704, 2020.
[15] Weerakody P B, Wong K W, Wang G, et al. A review of irregular time series data handling with gated recurrent neural networks[J]. Neurocomputing, 2021, 441: 161-178.
[16] Zhou T, Ma Z, Wen Q, et al. Film: Frequency improved legendre memory model for long-term time series forecasting[J]. Advances in neural information processing systems, 2022, 35: 12677-12690.
[17] García S, Luengo J, Herrera F. Data preprocessing in data mining[M]. Cham, Switzerland: Springer International Publishing, 2015.
[18] Cioffi J, Kailath T. Windowed fast transversal filters adaptive algorithms with normalization[J]. IEEE transactions on acoustics, speech, and signal processing, 2003, 33(3): 607-625.
[19] Bielza C, Li G, Larranaga P. Multi-dimensional classification with Bayesian networks[J]. International Journal of Approximate Reasoning, 2011, 52(6): 705-727.
[20] Wixted J T, Squire L R. The medial temporal lobe and the attributes of memory[J]. Trends in cognitive sciences, 2011, 15(5): 210-217.
[21] Huang Q, Shen L, Zhang R, et al. Crossgnn: Confronting noisy multivariate time series via cross interaction refinement[J]. Advances in Neural Information Processing Systems, 2023, 36: 46885-46902.
[22] Burton-Jones A, Hubona G S. The mediation of external variables in the technology acceptance model[J]. Information & management, 2006, 43(6): 706-717.
[23] Pan X, Luo P, Shi J, et al. Two at once: Enhancing learning and generalization capacities via ibn-net[C]//Proceedings of the european conference on computer vision (ECCV). 2018: 464-479.
[24] Wu H, Xu J, Wang J, et al. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting[J]. Advances in neural information processing systems, 2021, 34: 22419-22430.
[25] Taqqu M S, Teverovsky V, Willinger W. Estimators for long-range dependence: an empirical study[J]. Fractals, 1995, 3(04): 785-798.
[26] Rothe I, Susse H, Voss K. The method of normalization to determine invariants[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18(4): 366-376.
[27] Benhar H, Idri A, Fernández-Alemán J L. Data preprocessing for heart disease classification: A systematic literature review[J]. Computer Methods and Programs in Biomedicine, 2020, 195: 105635.
[28] Fessler J A, Sutton B P. Nonuniform fast Fourier transforms using min-max interpolation[J]. IEEE transactions on signal processing, 2003, 51(2): 560-574.
[29] Herrmann H, Bär H, Kreplak L, et al. Intermediate filaments: from cell architecture to nanomechanics[J]. Nature reviews Molecular cell biology, 2007, 8(7): 562-573.
[30] Chicco D, Warrens M J, Jurman G. The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation[J]. Peerj computer science, 2021, 7: e623.
[31] Stich S U. Local SGD converges fast and communicates little[J]. arXiv preprint arXiv:1805.09767, 2018.
[32] Shanghai Petroleum and Natural Gas Exchange. China LNG Comprehensive Import DES Price Index[EB/OL]. (2018-1-1) [Accessed: 2025-09-12]. https://www.shpgx.com/html/jkLNGdajg.html.
[33] China Foreign Exchange Trade System. RMB Central Parity Rate Announcement[EB/OL]. (2025-09-03) [Accessed: 2025-09-12]. https://www.chinamoney.org.cn/chinese/ccprnoticecontent/index.html? searchDate=2025-09-03.
[34] Shanghai Environment and Energy Exchange. Monthly Overview of National Carbon Market (2025)[EB/OL]. (2025-08-29) [Accessed: 2025-09-12]. https://overview.cneeex.com/qgtpfqjy/jysj/ydgk/ 2025n/.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Academic Journal of Management and Social Sciences
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
