Carbon Price Forecasting with Structural Breaks: A Comparative Study of Deep Learning Models

2025-11-07

AI Summary

Carbon price forecasting is highly challenging due to structural breaks induced by policy interventions and market shocks, as well as high-frequency noise. Existing approaches typically treat breakpoint detection, denoising, and modeling as disjoint stages and lack systematic evaluation of deep temporal models. To address this, we propose PELT-WT-TCN—a hybrid framework that unifies PELT-based structural break detection, wavelet-based multi-scale denoising, and Temporal Convolutional Networks (TCNs) into an end-to-end pipeline for structural decomposition, noise suppression, and time-series modeling. Evaluated on EUA carbon allowance data, our method achieves a 22.35% reduction in RMSE and an 18.63% reduction in MAE over benchmark models, and improves upon an undecomposed LSTM by over 70% in error reduction. It significantly enhances prediction accuracy, robustness, and interpretability, establishing a novel paradigm for modeling non-stationary carbon price series.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Planning, Routing, and Scheduling: Temporal Planning
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Systems and Infrastructure for Web, Mobile and WoT: Sustainability and carbon-aware systems for Web, mobile, and WoT

Abstract

Accurately forecasting carbon prices is essential for informed energy market decision-making, guiding sustainable energy planning, and supporting effective decarbonization strategies. However, it remains challenging due to structural breaks and high-frequency noise caused by frequent policy interventions and market shocks. Existing studies, including the most recent baseline approaches, have attempted to incorporate breakpoints but often treat denoising and modeling as separate processes and lack systematic evaluation across advanced deep learning architectures, limiting the robustness and the generalization capability. To address these gaps, this paper proposes a comprehensive hybrid framework that integrates structural break detection (Bai-Perron, ICSS, and PELT algorithms), wavelet signal denoising, and three state-of-the-art deep learning models (LSTM, GRU, and TCN). Using European Union Allowance (EUA) spot prices from 2007 to 2024 and exogenous features such as energy prices and policy indicators, the framework constructs univariate and multivariate datasets for comparative evaluation. Experimental results demonstrate that our proposed PELT-WT-TCN achieves the highest prediction accuracy, reducing forecasting errors by 22.35% in RMSE and 18.63% in MAE compared to the state-of-the-art baseline model (Breakpoints with Wavelet and LSTM), and by 70.55% in RMSE and 74.42% in MAE compared to the original LSTM without decomposition from the same baseline study. These findings underscore the value of integrating structural awareness and multiscale decomposition into deep learning architectures to enhance accuracy and interpretability in carbon price forecasting and other nonstationary financial time series.

Problem

• Forecasting carbon prices challenged by structural breaks and noise
• Existing methods lack integrated denoising and systematic deep learning evaluation
• Proposes hybrid framework combining break detection, denoising, and deep learning models

Innovation

• Integrates structural break detection with wavelet denoising
• Combines PELT, wavelet, and TCN for hybrid framework
• Uses multiscale decomposition to enhance deep learning accuracy