基于多模态多尺度特征的超短期光伏功率预测

陈殿昊; 臧海祥; 刘璟璇; 张越; 孙国强; 卫志农

doi:10.19912/j.0254-0096.tynxb.2024-0701

PDF(1981 KB)

太阳能学报 ›› 2025, Vol. 46 ›› Issue (8) : 472-480. DOI: 10.19912/j.0254-0096.tynxb.2024-0701

基于多模态多尺度特征的超短期光伏功率预测

陈殿昊, 臧海祥, 刘璟璇, 张越, 孙国强, 卫志农

作者信息 +

ULTRA-SHORT-TERM PHOTOVOLTAIC POWER FORECASTING BASED ON MULTI-MODAL MULTI-SCALE FEATURES

Chen Dianhao, Zang Haixiang, Liu Jingxuan, Zhang Yue, Sun Guoqiang, Wei Zhinong

Author information +

文章历史 +

摘要

为进一步提高超短期光伏功率预测的准确性,提出一种基于多模态多尺度特征的超短期光伏功率预测方法。首先,基于不同采样间隔得到多尺度地基云图与多尺度光伏功率作为预测模型的输入数据;其次,利用自注意卷积长短期记忆神经网络与长短期记忆神经网络分别提取多尺度云图数据的时空特征与多尺度功率数据的时序特征,从而得到多模态多尺度特征;然后,提出一种基于多头自注意力与多头交叉注意力的融合注意力机制,对多模态多尺度特征信息进行深度融合;最后,将多模态多尺度融合特征作为多层感知器的输入,进而实现超短期光伏功率预测。实验结果表明,该方法能够有效提高超短期光伏功率预测准确性。

Abstract

To further improve the accuracy of ultra-short-term photovoltaic power forecasting, a forecasting method based on multi-modal multi-scale features is proposed. Firstly, multi-scale historical cloud images and PV power are obtained based on different sampling intervals as the input data of the forecasting model. Secondly, the spatial and temporal features of multi-scale cloud image data and multi-scale power data are extracted using self-attention convolutional long short-term memory neural network and long short-term memory neural network respectively, to obtain multi-modal multi-scale features. Then, a fusion-attention mechanism based on multi-head self-attention and multi-head cross-attention is proposed to integrate multi-modal multi-scale feature information deeply. Finally, the multi-modal multi-scale fusion features are used as the input of multi-layer perceptron to achieve ultra-short-term photovoltaic power forecasting. Experimental results show that this method can effectively improve the accuracy of ultra-short-term photovoltaic power forecasting.

导出引用

陈殿昊, 臧海祥, 刘璟璇, 张越, 孙国强, 卫志农. 基于多模态多尺度特征的超短期光伏功率预测[J]. 太阳能学报. 2025, 46(8): 472-480 https://doi.org/10.19912/j.0254-0096.tynxb.2024-0701

Chen Dianhao, Zang Haixiang, Liu Jingxuan, Zhang Yue, Sun Guoqiang, Wei Zhinong. ULTRA-SHORT-TERM PHOTOVOLTAIC POWER FORECASTING BASED ON MULTI-MODAL MULTI-SCALE FEATURES[J]. Acta Energiae Solaris Sinica. 2025, 46(8): 472-480 https://doi.org/10.19912/j.0254-0096.tynxb.2024-0701

中图分类号： TM615

参考文献

[1] 焦丕华, 蔡旭, 王乐乐, 等. 考虑数据分解和进化捕食策略的BiLSTM短期光伏发电功率预测[J]. 太阳能学报, 2024, 45(2): 435-442.
JIAO P H, CAI X, WANG L L, et al.BiLSTM short-term photovoltaic power prediction considering data decomposition and evolutionary predation strategies[J]. Acta energiae solaris sinica, 2024, 45(2): 435-442.
[2] 崔京港, 王芳, 叶泽甫, 等. 基于QD和因果注意力TCN的光伏功率区间预测[J]. 太阳能学报, 2024, 45(3): 488-495.
CUI J G, WANG F, YE Z F, et al.Photovoltaic power interval prediction based on QD and causal attention TCN[J]. Acta energiae solaris sinica, 2024, 45(3): 488-495.
[3] 殷豪, 李奕甸, 谢智锋, 等. 混合图神经网络和门控循环网络的短期光伏功率预测[J]. 太阳能学报, 2024, 45(3): 523-532.
YIN H, LI Y D, XIE Z F, et al.Short-term photovoltaic power prediction method based on mixed graph neural network and gated recurrent unit network[J]. Acta energiae solaris sinica, 2024, 45(3): 523-532.
[4] 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.
[5] 柴闵康, 夏飞, 张浩, 等. 基于云图特征自识别的光伏超短期预测模型[J]. 电网技术, 2021, 45(3): 1023-1035.
CHAI M K, XIA F, ZHANG H, et al.Ultra-short-term prediction of self-identifying photovoltaic based on sky cloud chart[J]. Power system technology, 2021, 45(3): 1023-1035.
[6] 程礼临, 臧海祥, 卫志农, 等. 考虑多光谱卫星遥感的区域级超短期光伏功率预测[J]. 中国电机工程学报, 2022, 42(20): 7451-7465.
CHENG L L, ZANG H X, WEI Z N, et al.Ultra-short-term forecasting of regional photovoltaic power generation considering multispectral satellite remote sensing data[J]. Proceedings of the CSEE, 2022, 42(20): 7451-7465.
[7] CHENG L L, ZANG H X, WEI Z N, et al.Solar power prediction based on satellite measurements:a graphical learning method for tracking cloud motion[J]. IEEE transactions on power systems, 2022, 37(3): 2335-2345.
[8] PALETTA Q, HU A, ARBOD G, et al.ECLIPSE: envisioning cloud induced perturbations in solar energy[J]. Applied energy, 2022, 326: 119924.
[9] HUANG X Q, LIU J, XU S Z, et al.A 3D ConvLSTM-CNN network based on multi-channel color extraction for ultra-short-term solar irradiance forecasting[J]. Energy, 2023, 272: 127140.
[10] 谢小瑜, 周俊煌, 张勇军, 等. 基于W-BiLSTM的可再生能源超短期发电功率预测方法[J]. 电力系统自动化, 2021, 45(8): 175-184.
XIE X Y, ZHOU J H, ZHANG Y J, et al.W-BiLSTM based ultra-short-term generation power prediction method of renewable energy[J]. Automation of electric power systems, 2021, 45(8): 175-184.
[11] 李宏扬, 高丙朋. 基于改进VMD和SNS-Attention-GRU的短期光伏发电功率预测[J]. 太阳能学报, 2023, 44(8): 292-300.
LI H Y, GAO B P.Short-term PV power forecasting based on improved VMD and SNS-Attention-GRU[J]. Acta energiae solaris sinica, 2023, 44(8): 292-300.
[12] 滕陈源, 丁逸超, 张有兵, 等. 基于VMD-Informer-BiLSTM模型的超短期光伏功率预测[J]. 高电压技术, 2023, 49(7): 2961-2971.
TENG C Y, DING Y C, ZHANG Y B, et al.Ultra-short-term photovoltaic power prediction based on VMD-Informer-BiLSTM model[J]. High voltage engineering, 2023, 49(7): 2961-2971.
[13] FENG S B, MIAO C Y, XU K, et al.Multi-scale attention flow for probabilistic time series forecasting[J]. IEEE transactions on knowledge and data engineering, 2024, 36(5): 2056-2068.
[14] 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): 3527-3537.
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): 3527-3537.
[15] LIN Z H, LI M M, ZHENG Z B, et al.Self-attention ConvLSTM for spatiotemporal prediction[J]. Proceedings of the AAAI conference on artificial intelligence, 2020, 34(7): 11531-11538.
[16] 臧海祥, 张越, 程礼临, 等. 基于ICEEMDAN-LSTM和残差注意力的短期太阳辐照度预测[J]. 太阳能学报, 2023, 44(12): 175-181.
ZANG H X, ZHANG Y, CHENG L L, et al.Short term solar radiation forecasting based on ICEEMDAN-LSTM and residual attention[J]. Acta energiae solaris sinica, 2023, 44(12): 175-181.
[17] CAO J Z, YU L G, LING B W, et al.MHSAN: Multi-view hierarchical self-attention network for 3D shape recognition[J]. Pattern recognition, 2024, 150: 110315.
[18] WANG L, PENG J J, ZHENG C Z, et al.A cross modal hierarchical fusion multimodal sentiment analysis method based on multi-task learning[J]. Information processing & management, 2024, 61(3): 103675.
[19] NIE Y H, LI X T, SCOTT A, et al.SKIPP’D: a sky images and photovoltaic power generation dataset for short-term solar forecasting[J]. Solar energy, 2023, 255: 171-179.
[20] DOLATABADI A, ABDELTAWAB H, MOHAMED Y A I. Deep reinforcement learning-based self-scheduling strategy for a CAES-PV system using accurate sky images-based forecasting[J]. IEEE transactions on power systems, 2023, 38(2): 1608-1618.
[21] ZHU T T, GUO Y R, LI Z Y, et al.Solar radiation prediction based on convolution neural network and long short-term memory[J]. Energies, 2021, 14(24): 8498.
[22] FENG C, ZHANG J, ZHANG W Q, et al.Convolutional neural networks for intra-hour solar forecasting based on sky image sequences[J]. Applied energy, 2022, 310: 118438.
[23] KONG W C, JIA Y W, DONG Z Y, et al.Hybrid approaches based on deep whole-sky-image learning to photovoltaic generation forecasting[J]. Applied energy, 2020, 280: 115875.
[24] GB/T 40607—2021, 调度侧风电或光伏功率预测系统技术要求[S].
GB/T 40607—2021, Technical requirements for dispatching side forecasting system of wind or photovoltaic power[S].