李增伟,王娅云,张容福,马元明,方晨,魏永瑜
LI Zengwei,WANG Yayun,ZHANG Rongfu,MA Yuanming,FANG Chen,WEI Yongyu

• 1:国网青海省电力公司信息通信公司

摘要(Abstract)：

分布式光伏输出功率的随机性和波动性给电力调度工作的精准预测和调度决策带来了挑战。对此，提出一种基于SE-CNN-BiLSTM（压缩激励-卷积神经网络-双向长短期记忆）与改进Transformer的多时间尺度融合的光伏功率超短期预测模型及方法。首先，基于光伏功率的日趋势相似特性，提出一种融合通道注意力机制的特征提取方法，构建光伏输出功率趋势特征预测模型；接着，考虑光伏功率短期波动特性，提出一种基于STM（相似时间段匹配）的波动特征提取方法，利用光伏输出功率的天气波动特征构建基于改进Transformer的预测模型；然后，融合长、短时间尺度的光伏功率趋势特征和波动特征，构建多时间尺度融合的光伏功率预测方法。最后，结合实际光伏电站运行数据和仿真数据对提出的模型进行验证。结果表明，所提方法能有效提高预测模型的表征能力和预测精度。
The random and volatile distributed photovoltaic(PV) power pose challenges for accurate forecasting and dispatch decision-making in power system operations. To address this, A multi-timescale photovoltaic power prediction method based on SE-CNN-BiLSTM and improved Transformer is proposed. Firstly, leveraging the diurnal trend similarity characteristics of PV power, a feature extraction method incorporating a channel attention mechanism is proposed to construct a prediction model for PV power trend features. Subsequently, based on the short-term fluctuation characteristics of PV power, a fluctuation feature extraction method based on similar time-period matching(STM) is proposed, utilizing the weather-induced fluctuation features of PV power to build a prediction model based on an improved Transformer. Then, by fusing the long-and short-timescale trend features and fluctuation features of PV power, a multi-timescale fusion method for PV power prediction is constructed. Finally, the proposed model is validated using actual operational data from a PV power station and simulation data. Results demonstrate that the proposed method effectively enhances the representational capacity and prediction accuracy of the forecasting model.

关键词(KeyWords)： 光伏功率预测;注意力机制;LSTM;改进Transformer;特征融合
PV power prediction;attention mechanism;LSTM;improved Transformer;feature fusion

Abstract:

Keywords:

基金项目(Foundation): 国网青海省电力公司科技项目（52281424000C）

作者(Author): 李增伟,王娅云,张容福,马元明,方晨,魏永瑜
LI Zengwei,WANG Yayun,ZHANG Rongfu,MA Yuanming,FANG Chen,WEI Yongyu

DOI: 10.19585/j.zjdl.202603011

参考文献(References)：

• [1]郝文斌，孟志高，张勇，等.新型电力系统下多分布式电源接入配电网承载力评估方法研究[J].电力系统保护与控制，2023,51(14):23-33.HAO Wenbin,MENG Zhigao,ZHANG Yong,et al.Carrying capacity evaluation of multiple distributed power supply access to the distribution network with the background of a new power system[J].Power System Protection and Control,2023,51(14):23-33.
• [2]BAI R X,SHI Y T,YUE M,et al.Hybrid model based on K-means++algorithm,optimal similar day approach,and long short-term memory neural network for shortterm photovoltaic power prediction[J].Global Energy Interconnection,2023,6(2):184-196.
• [3]水恒华，顾阳，徐晓春，等.一种适用于光伏高渗透率地区的太阳辐照短时预测技术研究[J].电测与仪表，2024,61(4):149-154.SHUI Henghua,GU Yang,XU Xiaochun,et al.Research on a short-term solar radiation prediction technology for photovoltaic high permeability area[J].Electrical Measurement&Instrumentation,2024,61(4):149-154.
• [4]王东风，李青博，张博洋，等.考虑季节性与趋势特征的光伏功率预测模型研究[J].太阳能学报，2025,46(3):348-356.WANG Dongfeng,LI Qingbo,ZHANG Boyang,et al.Research on photovoltaic power prediction model considering seasonality and trend characteristics[J].Acta Energiae Solaris Sinica,2025,46(3):348-356.
• [5]陈凡，李智，丁津津，等.考虑光伏机理与数据驱动结合的短期功率预测[J].科学技术与工程，2023,23(20):8686-8692.CHEN Fan,LI Zhi,DING Jinjin,et al. Consider shortterm power prediction combining photovoltaic mechanism and data-driven[J].Science Technology and Engineering,2023,23(20):8686-8692.
• [6]仇琦，杨兰，丁旭，等.基于改进EMD-ARIMA的光伏发电系统短期功率预测[J].电力科学与工程，2020,36(8):42-50.QIU Qi,YANG Lan,DING Xu,et al.An improved shortterm power prediction method of PV power generation system based on EMD-ARIMA model[J].Electric Power Science and Engineering,2020,36(8):42-50.
• [7]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 Wei,SU Zhongyuan,SHI Jinlin,et al. Photovoltaic power forecasting based on dual-attention-gru and similarity modification[J].Acta Energiae Solaris Sinica,2024,45(3):480-487.
• [8]张静，熊国江.考虑季节特性与数据窗口的短期光伏功率预测组合模型[J].电力工程技术，2025,44(1):183-192.ZHANG Jing,XIONG Guojiang.Short-term photovoltaic power prediction combination model considering seasonal characteristic and data window[J]. Electric Power Engineering Technology,2025,44(1):183-192.
• [9]王涛，王旭，许野，等.计及相似日的LSTM光伏出力预测模型研究[J].太阳能学报，2023,44(8):316-323.WANG Tao,WANG Xu,XU Ye,et al. Study on lstm photovoltaic output prediction model considering similar days[J]. Acta Energiae Solaris Sinica,2023,44(8):316-323.
• [10]陈峰，余轶，徐敬友，等.基于Bayes-LSTM网络的风电出力预测方法[J].电力系统保护与控制，2023,51(6):170-178.CHEN Feng,YU Yi,XU Jingyou,et al. Prediction method of wind power output based on a Bayes-LSTM network[J].Power System Protection and Control,2023,51(6):170-178.
• [11]陈船宇，熊国江，方厚康，等.基于MODWT-CEEMDANLSTM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 Chuanyu,XIONG Guojiang,FANG Houkang,et al. Short-term photovoltaic power interval prediction model based on modwt-ceemdan-lstm[J]. Acta Energiae Solaris Sinica,2025,46(2):416-424.
• [12]戴朝辉，陈昊，刘莘轶，等.基于K-medoids-GBDT-PSOLSTM组合模型的短期光伏功率预测[J].太阳能学报，2025,46(1):654-661.DAI Zhaohui,CHEN Hao,LIU Xinyi,et al. Short-term photovoltaic power prediction based on k-medoids-gbdtpso-lstm combined model[J]. Acta Energiae Solaris Sinica,2025,46(1):654-661.
• [13]吐松江·卡日，雷柯松，马小晶，等.基于LSTM-Attention和CNN-BiGRU误差修正的光伏功率预测[J].太阳能学报，2024,45(12):85-93.KARI·Tusongjiang,LEI Kesong,MA Xiaojing,et al.Photovoltaic power prediction based on lstm-attention and cnnBiGRU error correction[J].Acta Energiae Solaris Sinica,2024,45(12):85-93.
• [14]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 Haitao,LI Wenjuan,LI Xuefeng,et al.Photovoltaic power forecasting based on TPA-TCN model and variational modal decomposition[J]. Electrical Measurement&Instrumentation,2024,61(12):156-163.
• [15]薛阳，燕宇铖，贾巍，等.基于改进灰狼算法优化长短期记忆网络的光伏功率预测[J].太阳能学报，2023,44(7):207-213.XUE Yang,YAN Yucheng,JIA Wei,et al. Photovoltaic power prediction model based on igwo-lstm[J].Acta Energiae Solaris Sinica,2023,44(7):207-213.
• [16]王晓霞，俞敏，冀明，等.基于气候相似性与SSA-CNNLSTM的光伏功率组合预测[J].太阳能学报，2023,44(6):275-283.WANG Xiaoxia,YU Min,JI Ming,et al. Photovoltaic power combination forecasting based on climate similarity and ssa-cnn-lstm[J].Acta Energiae Solaris Sinica,2023,44(6):275-283.
• [17]刘甚臻，马超.基于小波变换和混合深度学习的短期光伏功率预测[J].可再生能源，2023,41(6):744-749.LIU Shenzhen,MA Chao.Short-term photovoltaic power prediction based on wavelet transform and hybrid deep learning[J].Renewable Energy Resources,2023,41(6):744-749.
• [18]ZHAI C,HE X Y,CAO Z X,et al. Photovoltaic power forecasting based on VMD-SSA-Transformer:Multidimensional analysis of dataset length,weather mutation and forecast accuracy[J].Energy,2025,324:135971.
• [19]TANG H D,KANG F,LI X Y,et al.Short-term photovoltaic power prediction model based on feature construction and improved transformer[J]. Energy,2025,320:135213.
• [20]黄晓燕，郭洒洒，陈成优，等.考虑时空关联及气象耦合的区域分布式光伏功率预测[J].浙江电力，2025,44(3):79-89.HUANG Xiaoyan,GUO Sasa,CHEN Chengyou,et al.Regional distributed photovoltaic power forecasting considering spatiotemporal correlation and meteorological coupling[J].Zhejiang Electric Power,2025,44(3):79-89.
• [21]PIANTADOSI G,DUTTO S,GALLI A,et al.Photovoltaic power forecasting:a Transformer based framework[J].Energy and AI,2024,18:100444.
• [22]CHEN R J,LIU G,CAO Y S,et al.CGAformer:Multiscale feature Transformer with MLP architecture for shortterm photovoltaic power forecasting[J]. Energy,2024,312:133495.
• [23]ZHAO X. A novel digital-twin approach based on transformer for photovoltaic power prediction[J].Scientific Reports,2024,14:26661.
• [24]陆毅，薛枫，唐小波，等.基于余弦相似度和TSO-BP的短期光伏预测方法[J].浙江电力，2024,43(6):22-30.LU Yi,XUE Feng,TANG Xiaobo,et al.A short-term PV power forecasting method based on cosine similarity and TSO-BP neural network[J]. Zhejiang Electric Power,2024,43(6):22-30.
• [25]KIM J,OBREGON J,PARK H,et al.Multi-step photovoltaic power forecasting using transformer and recurrent neural networks[J]. Renewable and Sustainable Energy Reviews,2024,200:114479.
• [26]叶林，李奕霖，裴铭，等.寒潮天气小样本条件下的短期风电功率组合预测[J].中国电机工程学报，2023,43(2):543-554.YE Lin,LI Yilin,PEI Ming,et al.Short-term wind power combination forecast under the condition of small sample in cold wave weather[J].Proceedings of the CSEE,2023,43(2):543-554.
• [27]余光正，陆柳，汤波，等.考虑转折性天气的海上风电功率超短期分段预测方法研究[J].中国电机工程学报，2022,42(13):4859-4871.YU Guangzheng,LU Liu,TANG Bo,et al.Research on ultra-short-term subsection forecasting method of offshore wind power considering transitional weather[J].Proceedings of the CSEE,2022,42(13):4859-4871.