基于MODWT-CEEMDAN-Transformer-BiTCN的短期光伏功率区间预测

田博; 熊国江; 刘夜雨; 吴晨昊

doi:10.19912/j.0254-0096.tynxb.2025-0696

PDF(1685 KB)

太阳能学报 ›› 2026, Vol. 47 ›› Issue (9) : 252-259. DOI: 10.19912/j.0254-0096.tynxb.2025-0696

基于MODWT-CEEMDAN-Transformer-BiTCN的短期光伏功率区间预测

田博, 熊国江, 刘夜雨, 吴晨昊

作者信息 +

SHORT-TERM PHOTOVOLTAIC POWER INTERVAL PREDICTION BASED ON MODWT-CEEMDAN-TRANSFORMER-BiTCN

Tian Bo, Xiong Guojiang, Liu Yeyu, Wu Chenhao

Author information +

文章历史 +

摘要

提出一种基于最大重叠离散小波变换（MODWT）,融合自适应噪声完备集合经验模态分解（CEEMDAN）算法、双向时序卷积网络（BiTCN）与Transformer架构,构建一套面向光伏出力的区间预测组合模型。首先使用MODWT和CEEMDAN将光伏功率时间序列进行双重分解得到本征模态函数分量;其次根据斯皮尔曼相关系数将本征模态函数（IMF）划分为时序分量和随机分量;然后采用Transformer和BiTCN对时序分量和随机分量分别进行预测,并将两个通道的预测结果融合重构,获得点预测值;基于核密度估计方法,对点预测结果进行扩展,最终得到区间预测结果。算例表明,使用时域与时频域结合的双重信号分解,集成BiTCN与Transformer的双通道模型预测,相比于其他预测模型,准确度平均提升了29.36%。

Abstract

This paper proposes a hybrid interval prediction model for Photovoltaic （PV） output by integrating the maximal overlap discrete wavelet transform （MODWT）, complete ensemble empirical mode decomposition with adaptive noise （CEEMDAN）, Bi-directional Temporal Convolutional Network （BiTCN） and Transformer architecture. Firstly, MODWT and CEEMDAN are applied to perform dual decomposition of the PV power time series, yielding intrinsic mode function components. Secondly, the IMFs are categorized into temporal and stochastic components based on their Spearman correlation coefficients. Subsequently, the temporal components are predicted using Transformer, while the stochastic components are predicted using BiTCN. The prediction results from both pathways are then reconstructed to obtain point forecasts. Finally, the point forecasts are expanded into prediction intervals using a kernel density estimation method. Validation on actual case studies demonstrates that this approach, leveraging dual signal decomposition （time and time-frequency domains） and integrating the dual-channel network architecture （BiTCN and Transformer）, achieves an average accuracy improvement of 29.36 % compared to other benchmark prediction models.

导出引用

田博, 熊国江, 刘夜雨, 吴晨昊. 基于MODWT-CEEMDAN-Transformer-BiTCN的短期光伏功率区间预测[J]. 太阳能学报. 2026, 47(9): 252-259 https://doi.org/10.19912/j.0254-0096.tynxb.2025-0696

Tian Bo, Xiong Guojiang, Liu Yeyu, Wu Chenhao. SHORT-TERM PHOTOVOLTAIC POWER INTERVAL PREDICTION BASED ON MODWT-CEEMDAN-TRANSFORMER-BiTCN[J]. Acta Energiae Solaris Sinica. 2026, 47(9): 252-259 https://doi.org/10.19912/j.0254-0096.tynxb.2025-0696

中图分类号： TM615 TP18

参考文献

[1] 许多, 徐潇源, 秦放, 等. 面向光储电站运行收益提升的光伏功率价值导向预测方法[J]. 电力系统自动化, 2025, 49(4): 152-164.
Xu D, Xu X Y, Qin F, et al.Value-oriented photovoltaic power forecasting method for operation revenue improvement of photovoltaic-energy storage plants[J]. Automation of Electric Power Systems, 2025, 49(4): 152-164.
[2] 国家能源局. 2025年可再生能源并网运行情况[EB/OL]. https://www.nea.gov.cn/20260212/742b8c6a078347b0b39de676c05c5d58/c.html.
National Energy Administration. Grid-connected Operation of Renewable Energy Sources, 2025[EB/OL]. https://www.nea.gov.cn/20260212/742b8c6a078347b0b39de676c05c5d58/c.html.
[3] 唐剑飞. 光伏发电预测方法的分类与比较分析[J]. 船电技术, 2024, 44(9): 69-72.
Tang J F.Classification and comparative analysis of forecasting methods for photovoltaic power generation[J]. Marine Electric & Electronic Engineering, 2024, 44(9): 69-72.
[4] 王德文, 焦天媛. 基于二次分解的不同太阳辐射下光伏功率预测[J]. 太阳能学报, 2024, 45(9): 360-368.
Wang D W, Jiao T Y.Prediction of photovoltaic power under different solar radiation based on secondary decomposition[J]. Acta Energiae Solaris Sinica, 2024, 45(9): 360-368.
[5] 张海涛, 李文娟, 李雪峰, 等. 基于变分模态分解和时间注意力机制TCN网络的光伏发电功率预测[J]. 电测与仪表, 2024, 61(12): 156-163.
Zhang H T, Li W J, Li X F, et al.Photovoltaic power forecasting based on TPA-TCN model and variational modal decomposition[J]. Electrical Measurement & Instrumentation, 2024, 61(12): 156-163.
[6] 董俊, 刘瑞, 束洪春, 等. 基于BIRCH聚类的L-Transformer分布式光伏短期发电功率预测[J]. 高电压技术, 2024, 50(9): 3883-3893.
Dong J, Liu R, Shu H C, et al.Short-term distributed photovoltaic power generation prediction based on BIRCH cluster-ing and L-Transformer[J]. High Voltage Engineering, 2024, 50(9): 3883-3893.
[7] 赵如意, 王晓辉, 郑碧煌, 等. 基于特征优化和混合改进灰狼算法优化BiLSTM网络的短期光伏功率预测[J]. 电网技术, 2025, 49(1): 209-222.
Zhao R Y, Wang X H, Zheng B H, et al.Short-term photovoltaic power prediction based on feature optimization and hybrid improved grey wolf algorithm-optimized BiLSTM network[J]. Power System Technology, 2025, 49(1): 209-222.
[8] 何威, 苏中元, 史金林, 等. 基于双重注意力GRU与相似修正的光伏功率预测[J]. 太阳能学报, 2024, 45(3): 480-487.
He W, Su Z Y, Shi J L, et al.Photovoltaic power forecasting based on dual-attention-GRU and similarity modification[J]. Acta Energiae Solaris Sinica, 2024, 45(3): 480-487.
[9] 张建辉, 滕婕, 李秀慧, 等. 基于气象特征和改进Transformer的光伏功率短期预测[J]. 热能动力工程, 2024, 39(8): 146-154.
Zhang J H, Teng J, Li X H, et al.Short-term prediction of photovoltaic power based on meteorological features and improved Transformer[J]. Journal of Engineering for Thermal Energy and Power, 2024, 39(8): 146-154.
[10] 吴珺玥, 赵二刚, 郭增良, 等. 基于Spearman系数和TCN的光伏出力超短期多步预测[J]. 太阳能学报, 2023, 44(9): 180-186.
Wu J Y, Zhao E G, Guo Z L, et al.Ultra-short-term photovoltaic power multi-step prediction based on Spearman coefficient and tcn[J]. Acta Energiae Solaris Sinica, 2023, 44(9): 180-186.
[11] 何瑨麟, 郝建新, 苏成飞, 等. 基于SVMD-BO-BiTCN的超短期光伏发电功率预测[J]. 分布式能源, 2024, 9(5): 22-31.
He J L, Hao J X, Su C F, et al.Ultra-short-term photovoltaic power prediction based on SVMD-BO-BiTCN[J]. Distributed Energy, 2024, 9(5): 22-31.
[12] 毕贵红, 赵鑫, 李璐, 等. 双模式分解CNN-LSTM集成的短期风速预测模型[J]. 太阳能学报, 2023, 44(3): 191-197.
Bi G H, Zhao X, Li L, et al.Dual-mode decomposition CNN-LSTM integrated short-term wind speed forecasting model[J]. Acta Energiae Solaris Sinica, 2023, 44(3): 191-197.
[13] 赵耀, 高少炜, 李东东, 等. 基于天气相似聚类与QRNN的短期光伏功率区间概率预测[J]. 电力系统自动化, 2023, 47(23): 152-161.
Zhao Y, Gao S W, Li D D, et al.Short-term interval probability prediction of photovoltaic power based on weather similarity clustering and quantile regression neural network[J]. Automation of Electric Power Systems, 2023, 47(23): 152-161.
[14] 马乐乐, 孔小兵, 郭磊, 等. 基于最大重叠离散小波变换和深度学习的光伏功率预测[J]. 太阳能学报, 2024, 45(5): 576-583.
Ma L L, Kong X B, Guo L, et al.Photovoltaic power forecasting based on maximum overlap discrete wavelet transform and deep learning[J]. Acta Energiae Solaris Sinica, 2024, 45(5): 576-583.
[15] Zhang C, Hua L, Ji C L, et al.An evolutionary robust solar radiation prediction model based on WT-CEEMDAN and IASO-optimized outlier robust extreme learning machine[J]. Applied Energy, 2022, 322: 119518.
[16] 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): 949-957.
Xu Y, Li Q, Cui H.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): 949-957.
[17] 骆钊, 吴谕侯, 朱家祥, 等. 基于多尺度时间序列块自编码Transformer神经网络模型的风电超短期功率预测[J]. 电网技术, 2023, 47(9): 3527-3536.
Luo Z, Wu Y H, Zhu J X, et al.Wind power forecasting based on multi-scale time series block auto-encoder Transformer neural network model[J]. Power System Technology, 2023, 47(9): 3527-3536.
[18] Wang S X, Shi J R, Yang W, et al.High and low frequency wind power prediction based on Transformer and BiGRU-Attention[J]. Energy, 2024, 288: 129753.
[19] 李文武, 张鹏宇, 石强, 等. 基于聚合混合模态分解和时序卷积神经网络的综合能源系统负荷修正预测[J]. 电网技术, 2022, 46(9): 3345-3353.
Li W W, Zhang P Y, Shi Q, et al.Correction prediction of integrated energy system load based on aggregated mixed mode decomposition and TCN[J]. Power System Technology, 2022, 46(9): 3345-3353.
[20] 周思思, 李勇, 郭钇秀, 等. 考虑时序特征提取与双重注意力融合的TCN超短期负荷预测[J]. 电力系统自动化, 2023, 47(18): 193-205.
Zhou S S, Li Y, Guo Y X, et al.Ultra-short-term load forecasting based on temporal convolutional network considering temporal feature extraction and dual attention fusion[J]. Automation of Electric Power Systems, 2023, 47(18): 193-205.
[21] Zhang D D, Chen B A, Zhu H Y, et al.Short-term wind power prediction based on two-layer decomposition and BiTCN-BiLSTM-attention model[J]. Energy, 2023, 285: 128762.
[22] Pan C, Tan J, Feng D D.Prediction intervals estimation of solar generation based on gated recurrent unit and kernel density estimation[J]. Neurocomputing, 2021, 453: 552-562.
[23] 陈船宇, 熊国江, 方厚康, 等. 基于MODWT-CEEMDAN-LSTM的短期光伏功率区间预测模型[J]. 太阳能学报, 2025, 46(2): 416-424.
Chen C Y, Xiong G J, Fang H K, et al.Short-term photovoltaic power interval prediction model based on MODWT-CEEMDAN-LSTM[J]. Acta Energiae Solaris Sinica, 2025, 46(2): 416-424.
[24] 王耀健, 顾洁, 温洪林, 等. 基于在线高斯过程回归的短期风电功率概率预测[J]. 电力系统自动化, 2024, 48(11): 197-207.
Wang Y J, Gu J, Wen H L, et al.Short-term wind power probability prediction based on online Gaussian process regression[J]. Automation of Electric Power Systems, 2024, 48(11): 197-207.
[25] 杨国清, 李建基, 王德意, 等. 基于信息熵变权区间组合和边界逼近的短期光伏功率区间预测[J]. 太阳能学报, 2023, 44(2): 381-390.
Yang G Q, Li J J, Wang D Y, et al.Short-term photovoltaic power interval prediction based on information entropy variable weight interval combination and boundary approximation[J]. Acta Energiae Solaris Sinica, 2023, 44(2): 381-390.
[26] 蒋莹莹, 田建艳, 姬政雄, 等. 计及组合区间不确定性分析的光伏出力动静态赋权搜索预测模型[J]. 电网技术, 2024, 48(6): 2469-2479, I0056-I0059.
Jiang Y Y, Tian J Y, Ji Z X, et al. Dynamic and static weighted searching prediction model for PV outputs with combined interval uncertainty analysis[J]. Power System Technology, 2024, 48(6): 2469-2479, I0056-I0059.