AI-Driven LSTM-Copula Hybrid Model for Joint Risk Dependence Modelling in Carbon–Electricity Portfolio Management: Implications for Grid Cost-Effectiveness and Stability
DOI:
https://doi.org/10.4108/ew.12583Keywords:
carbon–electricity portfolio, Copula, CVaR, energy storage, grid stability, LSTM, risk dependence, VaRAbstract
INTRODUCTION: The increasing coupling between carbon emission trading and electricity markets creates significant joint risk challenging grid cost-effectiveness and stability. Existing approaches apply LSTM and Copula models separately, lacking a unified framework capturing both non-linear temporal dynamics and asymmetric tail dependence.
OBJECTIVES: This paper proposes an end-to-end LSTM-Copula hybrid model integrating deep learning-based marginal modeling with time-varying Copula dependence estimation for joint risk measurement and optimal portfolio allocation.
METHODS: The framework employs LSTM-GARCH for conditional mean and volatility modeling, EVT-GPD for tail fitting, and probability integral transform to obtain uniform variates. A time-varying t-Copula with DCC-type evolution captures dynamic joint dependence. Monte Carlo simulation estimates VaR and CVaR, followed by Min-CVaR portfolio optimization. Empirical analysis uses Chinese carbon and electricity market data (July 2021–December 2025).
RESULTS: The LSTM-GARCH model achieves RMSE reductions of 42.2% and 38.0% for carbon and electricity price prediction versus standalone GARCH. The integrated model attains a VaR failure rate of 5.2% at the 95% confidence level, outperforming GARCH-Copula, GARCH-Normal, and Historical Simulation in Kupiec and Christoffersen backtesting.
CONCLUSION: The proposed model provides a unified framework for carbon–electricity joint risk modeling, offering insights for AI-driven energy portfolio optimization and grid stability enhancement.
Downloads
References
[1] Y. Wang, S. Liu, M. Z. Abedin, and B. Lucey, "Volatility spillover and hedging strategies among Chinese carbon, energy, and electricity markets," J. Int. Financial Markets, Institutions and Money, vol. 91, art. 101938, 2024.
[2] K. Fang, "A study of risk spillovers between electricity and carbon markets," in Proc. IEEE 3rd Int. Conf. Power Science and Technology (ICPST), 2025, pp. 2035–2039.
[3] J. Yuan, W. Zhang, Q. Shen, L. Zhang, Y. Zhou, C. Zhao, J. Yang, and J. Zhang, "The impact of electricity-carbon market coupling on system marginal clearing price and power supply cost," Environ. Sci. Pollut. Res., vol. 30, pp. 84725–84741, 2023.
[4] J. Cao, M. S. Ho, R. Ma, and F. Teng, "When carbon emission trading meets a regulated industry: Evidence from the electricity sector of China," J. Public Econ., vol. 200, art. 104470, 2021.
[5] Y. Luo, S. Hong, and F. Guang, "The dynamic risk spillover effects among carbon, renewable energy, and electricity markets based on the TVP-VAR-DY model," Environ. Sci. Pollut. Res., vol. 31, pp. 30099–30111, 2024.
[6] T. Zhang and G. Strbac, "Artificial intelligence applications for energy storage: A comprehensive review," Energies, vol. 18, no. 17, art. 4718, 2025.
[7] C. Wang, Y. Ma, J. Xie, et al., "Multi-objective energy dispatch with deep reinforcement learning for wind–solar–thermal–storage hybrid systems," J. Energy Storage, vol. 105, art. 114635, 2025.
[8] R. Sepehrzad, A. S. G. Langeroudi, A. Khodadadi, S. Adinehpour, A. Al-Durra, and A. Anvari-Moghaddam, "An applied deep reinforcement learning approach to control active networked microgrids in smart cities with multi-level participation of battery energy storage system and electric vehicles," Sustain. Cities Soc., vol. 107, art. 105352, 2024.
[9] M. A. Naeem and N. Arfaoui, "Exploring downside risk dependence across energy markets: Electricity, conventional energy, carbon, and clean energy during episodes of market crises," Energy Econ., vol. 127, art. 107082, 2023.
[10] Y. Wu, W. Ren, Y. Xiong, G. Cao, P. Liang, and W. Zeng, "Return and volatility connectedness among carbon and energy markets based on time- and frequency-domain approaches," Frontiers Environ. Sci., vol. 11, art. 1315893, 2024.
[11] Y. Huang, X. Dai, Q. Wang, and D. Zhou, "A hybrid model for carbon price forecasting using GARCH and long short-term memory network," Appl. Energy, vol. 285, art. 116485, 2021.
[12] M. Cheng, K. Xu, G. Geng, H. Liu, and H. Wang, "Carbon price prediction based on advanced decomposition and long short-term memory hybrid model," J. Cleaner Prod., vol. 451, art. 142101, 2024.
[13] V. Pentsos, S. Tragoudas, J. Wibbenmeyer, and N. Khdeer, "A hybrid LSTM-Transformer model for power load forecasting," IEEE Trans. Smart Grid, vol. 16, pp. 2624–2634, 2025.
[14] N. Nauman, S. Akram, M. Rashid, A. Jaffar, S. Bhatti, and B. Fida, "Dual-model approach for concurrent forecasting of electricity prices and loads in smart grids: Comparison of sparse encoder NAR and GA-optimized LSTM," PLOS One, vol. 20, 2025.
[15] X. Wang and L. Yan, "Measuring the integrated risk of China's carbon financial market based on the copula model," Environ. Sci. Pollut. Res., vol. 29, pp. 54108–54121, 2022.
[16] T. S. Alotaibi, L. Dalla Valle, and M. J. Craven, "The worst case GARCH-copula CVaR approach for portfolio optimisation: Evidence from financial markets," J. Risk Financial Manage., vol. 15, no. 10, art. 482, 2022.
[17] H. Manner, F. A. Fard, A. Pourkhanali, and L. Tafakori, "Forecasting the joint distribution of Australian electricity prices using dynamic vine copulae," Energy Econ., vol. 78, pp. 143–164, 2019.
[18] S. Liu, Y. Zhang, J. Wang, and D. Feng, "Fluctuations and forecasting of carbon price based on a hybrid ensemble learning GARCH-LSTM-based approach: A case of five carbon trading markets in China," Sustainability, vol. 16, no. 4, 2024.
[19] F. Paraschiv, R. Hadzi-Mishev, and D. Keles, "Extreme value theory for heavy tails in electricity prices," J. Energy Markets, vol. 9, no. 2, pp. 21–50, 2016.
[20] K. Chan and P. Gray, "Using extreme value theory to measure value-at-risk for daily electricity spot prices," Int. J. Forecasting, vol. 22, pp. 283–300, 2006.
[21] A. Xuan, X. Shen, Q. Guo, and H. Sun, "A conditional value-at-risk based planning model for integrated energy system with energy storage and renewables," Appl. Energy, vol. 294, art. 116971, 2021.
[22] J. Gao, Y. Sun, and X. Su, "A risk preference-based optimization model for user-side energy storage system configuration from the investor's perspective," Electricity, vol. 6, no. 1, art. 3, 2025.
[23] S. Jeon, H. T. Nguyen, and D.-H. Choi, "Safety-integrated online deep reinforcement learning for mobile energy storage system scheduling and volt/var control in power distribution networks," IEEE Access, vol. 11, pp. 34440–34455, 2023.
[24] R. T. Rockafellar, S. Uryasev, "Optimization of conditional value-at-risk," Journal of Risk, 2000, 2(3): 21-41.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Runxin Hua
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 4.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
