| 云坡,杨玉.基于CEEMDAN-GRU混合多尺度模型的欧盟碳价预测研究[J].安徽建筑大学学报,2024,32(): |
| 基于CEEMDAN-GRU混合多尺度模型的欧盟碳价预测研究 |
| Forecasting European Carbon Price Based on CEEMDAN-GRU Hybrid Multis-cale Model |
| 投稿时间：2023-06-06 修订日期：2023-10-09 |
| DOI： |
| 中文关键词: 碳排放权价格 预测 CEEMDAN-GRU模型 多尺度 |
| 英文关键词: carbon emission pricing prediction CEEMDAN-GRU model multi-scale |
| 基金项目:安徽省哲学社会科学规划项目“多源异构时频信息环境下我国碳排放权价格机制刻画与建模预测”（项目编号：AHSKQ2022D040） |
|
| 摘要点击次数: 548 |
| 全文下载次数: 150 |
| 中文摘要: |
| 价格机制是碳排放权市场的核心，研究碳排放权市场化交易中的价格预测问题是推动碳市场减排作用发挥、破解能源约束的关键。基于碳价特有的非线性非平稳和多尺度特征，构建CEEMDAN-GRU混合多尺度模型，对碳排放权价格进行非线性预测，并进行样本外期限异质性检验。结果显示，相比EMD、CEEMD技术与LSTM、BP所构建的混合模型而言，CEEMDAN-GRU模型能有效捕捉碳价多尺度时频特征，实现分解误差的有效降低，预测误差RMSE、MAE、MAPE仅为1.0218、0.6815和0.0110，碳价预测精度优于基准模型，特别是短期预测效果呈现良好的鲁棒性，研究结论为投资者研判市场行情、开展量化分析提供参考。 |
| 英文摘要: |
| The price mechanism is the core of the carbon emission rights market, and studying the price prediction issues is the key to promoting carbon market emission reduction and breaking energy constraints. Based on the nonlinear non-stationary and multi-scale characteristics of carbon prices, a CEEMDAN-GRU hybrid forecasting model is constructed to perform nonlinear prediction of carbon prices, and then the out of sample term heterogeneity prediction is tested to provide the model robustness.The results show that, compared with the hybrid models constructed by EMD, CEEMD technologies, and LSTM, BP models, the CEEMDAN-GRU model can effectively capture the multi-scale time-frequency characteristics of carbon prices, with the forecasting errors of RMSE, MAE and MAPE are 1.0218, 0.6815 and 0.0110. The carbon price forecasting accuracy is superior to the benchmark models, especially the short-term forecasting performance. The conclusion provides a reference for investors to assess market conditions and conduct quantitative analysis. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
