A dual-attention TCN-BiGRU short-term electricity-carbon price coupling prediction method incorporating time-series fluctuation information mining

LIU Siyu; ZHANG Cheng; JIANG Tao; XIAO Ya; YI Yawen; ZHANG Yuxin; CHEN Xinyu

doi:10.11930/j.issn.1004-9649.202601038

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

A dual-attention TCN-BiGRU short-term electricity-carbon price coupling prediction method incorporating time-series fluctuation information mining

更新时间：2026-07-01

- A dual-attention TCN-BiGRU short-term electricity-carbon price coupling prediction method incorporating time-series fluctuation information mining
- Vol. 59, Issue 6, Pages: 60-75(2026)
- 作者机构：
  
  1. 国网湖北省电力有限公司,湖北,武汉,430075
  2. 华中科技大学电气与电子工程学院,湖北,武汉,430074
- 作者简介：
- 基金信息：
- DOI：10.11930/j.issn.1004-9649.202601038
  CLC：
- Online First：22 June 2026，
  
  Published：2026
- 稿件说明：
移动端阅览
刘思宇, 张成, 江涛, 肖雅, 易雅雯, 张玉欣, 陈新宇. 考虑时序波动信息挖掘的双重注意力TCN-BiGRU短期电-碳价格耦合预测方法[J]. 中国电力, 2026, 59(6): 60-75.

LIU Siyu, ZHANG Cheng, JIANG Tao, et al. A dual-attention TCN-BiGRU short-term electricity-carbon price coupling prediction method incorporating time-series fluctuation information mining[J]. 2026, 59(6): 60-75.
刘思宇, 张成, 江涛, 肖雅, 易雅雯, 张玉欣, 陈新宇. 考虑时序波动信息挖掘的双重注意力TCN-BiGRU短期电-碳价格耦合预测方法[J]. 中国电力, 2026, 59(6): 60-75. DOI： 10.11930/j.issn.1004-9649.202601038.

LIU Siyu, ZHANG Cheng, JIANG Tao, et al. A dual-attention TCN-BiGRU short-term electricity-carbon price coupling prediction method incorporating time-series fluctuation information mining[J]. 2026, 59(6): 60-75. DOI： 10.11930/j.issn.1004-9649.202601038.

摘要

短期现货实时电价与碳价的精准预测是电力市场交易、碳市场运作及两者协同管理的重要决策支撑。然而，电、碳价格序列共同受到能源结构、政策调控与可再生能源波动等多重复杂因素的交互影响，呈现出高波动、非线性的特征，对预测精度提出了更高挑战。因此，提出一种考虑时序波动信息挖掘的双重注意力时间卷积网络-双向门控循环网络（dual-attention temporal convolutional network，bidirectional gated recurrent network，DA-TCN-BiGRU）短期电-碳价格耦合预测方法。首先，采用中心碰撞优化变分模态分解算法将电价、碳价序列分别分解为多频率子序列，以充分提取其在不同时间尺度上的波动模态。然后，基于最大互信息系数评估高维特征集中各特征与电碳价间的关联强度，筛选出关键特征，构建DA-TCN-BiGRU深度学习模型对碳价进行预测，进而将碳价预测值作为关键外生变量输入同一框架对电价进行预测，实现电-碳价格的递进式耦合预测。最后，基于湖北省电碳市场实际数据的算例进行分析验证。结果表明，所提方法在电-碳价格预测中均具有更高的精度与更强的稳定性，验证了模型的有效性与优越性。

Abstract

Accurate forecasting of short-term spot electricity and carbon prices is crucial for decision-making in electricity market trading

carbon market operation

and their coordinated management. However

electricity and carbon price series are influenced by multiple complex factors

including energy structure

policy regulation

and renewable energy fluctuations

exhibiting high volatility and nonlinearity

which poses significant challenges to forecasting accuracy. Therefore

this paper proposes a dual-attention temporal convolutional network

bidirectional gated recurrent network (DA-TCN-BiGRU) short-term electricity-carbon price coupling forecasting method considering time-series fluctuation information mining. First

the central collision optimization-based variational mode decomposition algorithm is used to decompose the electricity and carbon price series into multi-frequency subsequences

so as to fully extract their fluctuation modes at different time scales. Second

the correlation strength between each feature in the high-dimensional feature set and electricity-carbon prices is evaluated based on the maximal information coefficient

and key features are selected. On this basis

a dual-attention TCN-BiGRU deep learning model is constructed to forecast carbon prices

and the predicted carbon price values are further input into the same framework as key exogenous variables to predict electricity prices

achieving progressive coupling forecasting of electricity-carbon prices. Finally

the case study based on actual data from the Hubei Province electricity-carbon market shows that the proposed method has higher accuracy and stronger stability in electricity-carbon price prediction

verifying the effectiveness and superiority of the model.

关键词

Keywords

references

2崔勇, 郑建, 时瑞廷, 等. 电-碳-绿证市场交易环境下多能联盟低碳优化运营机制研究[J]. 太阳能学报, 2025, 46 (12): 385- 395.

CUI Yong, ZHENG Jian, SHI Ruiting, et al. Research on low-carbon optimal operation mechanism of multi-energy alliance in electricity-carbon-green certificate market trading environment[J]. Acta Energiae Solaris Sinica, 2025, 46 (12): 385- 395.

3陈操操, 于凤菊, 张悦, 等. 碳交易试点政策减排效应实证评估及机制分析[J]. 中国环境科学, 2025, 45 (3): 1674- 1685.

CHEN Caocao, YU Fengju, ZHANG Yue, et al. Empirical evaluation and mechanism analysis of domestic carbon trading pilot policies on emission reduction[J]. China Environmental Science, 2025, 45 (3): 1674- 1685.

4蔡子龙, 李嘉棋, 沈赋, 等. 基于SDAE-EEMD降噪分解与改进Informer-BiLSTM模型的电力短期负荷预测方法[J]. 电网技术, 2025, 49 (12): 5009- 5018.

CAI Zilong, LI Jiaqi, SHEN Fu, et al. A Short-term power load forecasting method based on SDAE-EEMD denoising decomposition and an improved informer-BiLSTM model[J]. Power System Technology, 2025, 49 (12): 5009- 5018.

5王雨珊. 京津冀区域电力行业碳排放结构演化路径研究[D]. 北京: 华北电力大学(北京), 2024.

WANG Yushan. Research on the evolution path of carbon emission structure of electric power sector in Beijing-Tianjin-Hebei region[D]. Beijing: North China Electric Power University (Beijing), 2024 .

6张卓拉. 碳市场-用能权市场-电力市场价格传导模型研究[D]. 北京: 华北电力大学(北京), 2024.

ZHANG Zhuola. Research on the price transmission model of carbon market-energy consumption rights market-electricity market[D]. Beijing: North China Electric Power University (Beijing), 2024 .

7OLMSTEAD D E H, YATCHEW A. Carbon pricing and Alberta's energy-only electricity market[J]. The Electricity Journal, 2022, 35 (4): 107- 112.

8周明, 严正, 倪以信, 等. 含误差预测校正的 ARIMA 电价预测新方法[J]. 中国电机工程学报, 2004, 24 (12): 63- 68.

ZHOU Ming, YAN Zheng, NI Yixing, et al. A novel ARIMA approach on electricity price forecasting with the improvement of predicted error[J]. Proceedings of the CSEE, 2004, 24 (12): 63- 68.

9TAN Z F, ZHANG J L, WANG J L, et al. Day-ahead electricity price forecasting using wavelet transform combined with ARIMA and GARCH models[J]. Applied Energy, 2010, 87 (11): 3606- 3610.

10刘丽燕. 基于非参数GARCH模型的电力市场日前电价预测研究[D]. 重庆: 重庆师范大学, 2016.

LIU Liyan. Day-ahead of electricity price forecasting using nonparametric GARCH model [D]. Chongqing: Chongqing Normal University, 2016 .

11QIAO G X, WANG J H, ZHANG F P, et al. Structural changes and volatility forecasting in China's carbon markets: a hybrid approach integrating GARCH-SVR with LASSO-weighted windows method[J]. Journal of Climate Finance, 2025, 12: 100072.

12贾嵘, 蔡振华, 康睿. 基于最小二乘支持向量机的系统边际电价预测[J]. 高电压技术, 2006 (11): 145- 148.

JIA Rong, CAI Zhenhua, KANG Rui. Forecasting system marginal price based on similarity search and least square support vector machine[J]. High Voltage Engineering, 2006 (11): 145- 148.

13LUO R, LIU J P, CHEN P P, et al. Enhancing carbon price robust forecasting: A text-driven method utilizing weighted interval-joint quadratic support vector regression[J]. Energy Economics, 2025, 148, 108585.

14魏勤, 陈仕军, 黄炜斌, 等. 利用随机森林回归的现货市场出清价格预测方法[J]. 中国电机工程学报, 2021, 41 (4): 1360- 1367, 1542.

WEI Qin, CHEN Shijun, HUANG Weibin, et al. Forecasting method of clearing price in spot market by random forest regression[J]. Proceedings of the CSEE, 2021, 41 (4): 1360- 1367, 1542.

15ZHAO S Y, WANG Y L, DENG J W, et al. An adaptive multi-factor integrated forecasting model based on periodic reconstruction and random forest for carbon price[J]. Applied Soft Computing, 2025, 177, 113274.

16艾雨, 贾燕冰, 韩肖清. 基于相似日筛选与组合深度学习模型的日前电价预测方法[J]. 电网技术, 2025, 49 (1): 242- 251.

AI Yu, JIA Yanbin, HAN Xiaoqing. Day-ahead electricity price prediction method based on similar day screening and combined deep learning modeling[J]. Power System Technology, 2025, 49 (1): 242- 251.

17SHI H X, WEI A L, XU X Z, et al. A CNN-LSTM based deep learning model with high accuracy and robustness for carbon price forecasting: a case of Shenzhen's carbon market in China[J]. Journal of Environmental Management, 2024, 352, 120131.

18朱晋, 程启明, 程尹曼. 基于CNN-GRU深度学习的模块化多电平矩阵变换器故障诊断[J]. 南方电网技术, 2024, 18 (11): 13- 22.

ZHU Jin, CHENG Qiming, CHENG Yinman. Fault Diagnosis of modular multilevel matrix converter based on CNNGRU deep learning[J]. Southern Power System Technology, 2024, 18 (11): 13- 22.

19PALANIYAPPAN B, RAMU S K. Optimized LSTM-based electric power consumption forecasting for dynamic electricity pricing in demand response scheme of smart grid[J]. Results in Engineering, 2025, 25, 104356.

20乔松博, 孙瑜, 胡海, 等. 基于REMD-CNN-Transformer-LSTM组合模型的碳排放交易价格预测[J]. 西安理工大学学报, 2025, 41 (2): 186- 196.

QIAO Songbo, SUN Yu, HU Hai, et al. Carbon emission trading price prediction based on REMD CNN-Transformer-LSTM combined model[J]. Journal of Xi'an University of Technology, 2025, 41 (2): 186- 196.

21LI H Z, SHAO T M, GAO X, et al. Forecasting carbon price using a hybrid framework based on Bayesian optimization algorithm[J]. Petroleum Science, 2025, 22 (12): 5314- 5328.

22AKTER K, RAHMAN M A, ISLAM M R, et al. Data reconstruction-enabled robust hybrid models for intraday electricity price forecasting against data contamination attacks[J]. International Journal of Electrical Power & Energy Systems, 2026, 174: 111526.

23LI M, WANG X. Short-term electricity price forecasting via CPO-enhanced dual decomposition and NRBO-optimized deep learning[J]. Digital Signal Processing, 2026, 168(Part B): 105520.

24李子凯, 杨波, 周忠堂, 等. 考虑高比例风电波动的多注意力TCN电价预测方法[J]. 电测与仪表, 2025, 62 (3): 138- 146.

LI Zikai, YANG Bo, ZHOU Zhongtang, et al. A Multi-attention TCN based electricity price forecasting method considering high proportion of wind power fluctuation[J]. Electrical Measurement & Instrumentation, 2025, 62 (3): 138- 146.

25CAI X T, YUAN B, WU C. An integrated CEEMDAN and TCN-LSTM deep learning framework for forecasting[J]. International Review of Financial Analysis, 2025, 98, 103879.

26吉兴全, 曾若梅, 张玉敏, 等. 基于注意力机制的CNN-LSTM短期电价预测[J]. 电力系统保护与控制, 2022, 50 (17): 125- 132.

JI Xingquan, ZENG Ruomei, ZHANG Yumin, et al. CNN-LSTM short-term electricity price prediction based on an attention mechanism[J]. Power System Protection and Control, 2022, 50 (17): 125- 132.

27杨超, 冉启武, 罗德虎, 等. 基于注意力机制的CNN-BIGRU短期电价预测[J]. 电力系统及其自动化学报, 2024, 36 (3): 22- 29.

YANG Chao, RAN Qiwu, LUO Dehu, et al. Short-term electricity price prediction based on attention mechanism with CNN-BIGRU[J]. Proceedings of the CSU-EPSA, 2024, 36 (3): 22- 29.

28XU Y Z, HUANG X, GAO Z, et al. A novel electricity price forecasting approach based on multi-attention feature fusion model optimized by variational mode decomposition[J]. Measurement, 2025, 253(Part B): 117596.

29HUANG J Y, YU E, LI C J, et al. A hybrid attention-enabled multivariate information fusion for carbon price forecasting[J]. Renewable Energy, 2026, 256(Part E): 124246.

30刘达, 牛东晓, 李媛媛, 等. 基于周期波动及其影响分析的电力市场中长期电价预测[J]. 中国电机工程学报, 2009, 29 (13): 80- 85.

LIU Da, NIU Dongxiao, LI Yuanyuan, et al. Medium and long term electricity price forecasting in electricity market based on periodic fluctuation and its influence analysis[J]. Proceedings of the CSEE, 2009, 29 (13): 80- 85.

31许越, 李强, 崔晖. 基于MIC-EEMD-改进Informer的含高比例清洁能源与储能的电力市场短期电价多步预测[J]. 电网技术, 2024, 48 (3): 949- 958.

XU Yue, LI Qiang, CUI Hui. Short-term multi-step price prediction for the electricity market with a high proportion of clean energy and energy storage based on MIC-EEMD-improved informer[J]. Power System Technology, 2024, 48 (3): 949- 958.

32王长春, 王果, 赵倩宇, 等. 考虑分时电价和充电利用率特征的大型电动汽车充电站负荷短期预测方法[J]. 南方电网技术, 2024, 18 (5): 75- 84.

WANG Changchun, WANG Guo, ZHAO Qianyu, et al. A short-term load forecasting method for large scale electric vehicle charging stations considering characteristics of charging utilization rate and time-of-use electricity price[J]. Southern Power System Technology, 2024, 18 (5): 75- 84.

33TIAN Z R, SUN W P, WU C Y. MLP-Carbon: a new paradigm integrating multi-frequency and multi-scale techniques for accurate carbon price forecasting[J]. Applied Energy, 2025, 383, 125330.

34SHEN W J, WANG C, HUANG M M, et al. Multiple complex construction noise signal decomposition and prediction methods: based on WOA-VMD and stacked LSTM[J]. Measurement, 2025, 256(Part B): 118201.

35薛阳, 李金星, 杨江天, 等. 基于相似日分析和改进鲸鱼算法优化LSTM网络模型的光伏功率短期预测[J]. 南方电网技术, 2024, 18 (11): 97- 105.

XUE Yang, LI Jinxing, YANG Jiangtian, et al. Short-term prediction of photovoltaic power based on similar day analysis and improved whale algorithm to optimize LSTM network model[J]. Southern Power System Technology, 2024, 18 (11): 97- 105.

36KOHÚT R, KLAUČO M, KVASNICA M. Unified carbon emissions and market prices forecasts of the power grid[J]. Applied Energy, 2025, 377: 124527.

37YAN K, ZHANG D. Feature selection and analysis on correlated gas sensor data with recursive feature elimination[J]. Sensors Actuators B Chem, 2015, 212, 353- 63.

38JIANG Z Y, CHE J X, HE M J, et al. A CGRU multi-step wind speed forecasting model based on multi-label specific XGBoost feature selection and secondary decomposition[J]. Renewable Energy, 2023, 203, 802- 827.

39LANG Y F, GAO Y L, CHEN T T, et al. Centered Collision Optimizer: A novel and efficient physics-based metaheuristic optimization algorithm for solving complex real-world engineering optimization problems[J]. Computer Methods in Applied Mechanics and Engineering, 2026, 448(Part B): 118491.

40WANG J Y, XU P C, JI X B, et al. MIC-SHAP: An ensemble feature selection method for materials machine learning[J]. Materials Today Communications, 2023, 37, 106910.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Detection of Electricity Theft by Low Voltage Users with Zero Power Consumption Based on Water-Electricity Correlation Information

Load Forecasting Based on Multiple Load Features and TCN-GRU Neural Network

Abnormal data detection method for distribution networks in data scarcity scenarios

Intelligent substation model conversion method based on multi-dimensional similarity optimization and XSLT

The connotation, characteristics and construction ideas of the new rural energy system

Related Author

Nian ZOU

Meifang WEI

Sheng SU

Yingjun ZHENG

Wenqing ZHOU

Haofeng ZHENG

Guohua YANG

Wenjun KANG

Related Institution

School of Electrical & Information Engineering, Changsha University of Science and Technology

Technical Skills Training Center of State Grid Hunan Electric Power Co., Ltd.

School of Physics and Electronic-Electrical Engineering, Ningxia University

Electric Power Research Institute of State Grid Ningxia Electric Power Company

Electric Power Science Research Institute of Guangdong Power Grid Co., Ltd.

AI问答

⁰