| 云坡,周映彤,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(2):73-79 |
| 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 Multi-scale Model |
| |
| DOI： |
| 中文关键词: 碳价 预测 CEEMDAN-GRU模型 多尺度 |
| 英文关键词: carbon price prediction CEEMDAN-GRU model multi-scale |
| 基金项目:安徽省哲学社会科学规划青年项目（AHSKQ2022D040） |
|
| 摘要点击次数: 1100 |
| 全文下载次数: 0 |
| 中文摘要: |
| 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，对碳价进行非线性预测，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稳健性。 |
| 英文摘要: |
| Based on the nonlinear, non-stationary and multi-scale characteristics of carbon prices, a CEEMDAN-GRU hybridforecasting model was constructed to perform nonlinear prediction of carbon price, and the out-of-sample term heterogeneity predictionwas used to examine its robustness. The results showed 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 carbonprices, with the forecasting errors of RMSE, MAE and MAPE reaching 1.021 8, 0.681 5 and 0.011 0, respectively. The carbon priceforecasting accuracy was superior to the benchmark models, especially the short-term forecasting performance. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
