AI-Driven LSTM-Copula Hybrid Model for Joint Risk Dependence Modelling in Carbon–Electricity Portfolio Management: Implications for Grid Cost-Effectiveness and Stability
LSTM-Copulaハイブリッドモデルによる炭素・電力ポートフォリオ管理の共同リスク依存性モデリング：グリッドの費用対効果と安定性への示唆 (AI 翻訳)
Runxin Hua
🤖 gxceed AI 要約
日本語
本論文は、LSTMと時変Copulaを統合したハイブリッドモデルを提案し、中国の炭素排出権取引と電力市場の連動リスクを分析。LSTM-GARCHで非線形時系列特性を捉え、EVT-GPDで裾野リスクをモデル化、時変t-Copulaで動的従属構造を推定する。従来手法と比較して予測精度とVaR推定性能が向上し、グリッドの費用対効果と安定性向上に資する知見を提供する。
English
This paper proposes an end-to-end LSTM-Copula hybrid model for joint risk modeling in carbon-electricity markets. Using Chinese market data from 2021–2025, the model integrates LSTM-GARCH for marginal forecasts, EVT for tail risk, and time-varying Copula for dynamic dependence. It achieves 42.2% and 38.0% RMSE reduction in carbon and electricity price predictions, and a VaR failure rate of 5.2% at 95% confidence, outperforming conventional methods. The framework offers insights for AI-driven portfolio optimization and grid stability.
Unofficial AI-generated summary based on the public title and abstract. Not an official translation.
📝 gxceed 編集解説 — Why this matters
日本のGX文脈において
日本では、カーボンプライシングの本格化（東京都キャップ＆トレードなど）と電力市場の自由化が進む中、両市場の連動リスク管理が重要性を増している。本モデルは、日本の炭素・電力ポートフォリオにも適用可能であり、グリッド安定化やESG投資の高度化に寄与する可能性がある。
In the global GX context
Globally, the tightening coupling of carbon and electricity markets poses systemic risks for grid operators and investors. This study's AI-driven hybrid model provides a unified framework for joint risk measurement and optimal portfolio allocation, directly applicable to markets covered by the EU ETS, RGGI, and emerging carbon markets. It advances the use of deep learning in transition finance and energy portfolio management.
👥 読者別の含意
🔬研究者:Novel integration of LSTM and time-varying Copula for carbon-electricity joint risk modeling; benchmark for future AI-based energy risk studies.
🏢実務担当者:Offers a deployable framework for energy portfolio managers and grid operators to quantify and hedge joint carbon-electricity risks, improving cost-effectiveness.
🏛政策担当者:Provides evidence of how AI can enhance grid stability and market efficiency in carbon-pricing regimes, informing regulatory design for coupled markets.
📄 Abstract（原文）
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.
🔗 Provenance — このレコードを発見したソース
- semanticscholar https://publications.eai.eu/index.php/ew/article/download/12583/4185first seen 2026-07-23 05:54:29
🔔 こうした論文の新着を逃したくない方は キーワードアラート に登録（無料・3キーワードまで）。
gxceed は公開メタデータに基づく研究支援データセットです。要約・翻訳・解説は AI 支援で生成されています。 最終的な解釈・検証は利用者が原典資料に基づいて行うことを前提とします。