基于云图相位相关和低秩特征提取的超短期辐照度预测

郭吉强; 徐旭东; 张帅; 任密蜂; 王芳; 阎高伟

doi:10.19912/j.0254-0096.tynxb.2023-1799

PDF(3839 KB)

太阳能学报 ›› 2025, Vol. 46 ›› Issue (3) : 494-503. DOI: 10.19912/j.0254-0096.tynxb.2023-1799

基于云图相位相关和低秩特征提取的超短期辐照度预测

郭吉强¹, 徐旭东², 张帅², 任密蜂¹, 王芳¹, 阎高伟¹

作者信息 +

ULTRA-SHORT-TERM IRRADIANCE PREDICTION BASED ON CLOUD IMAGES PHASE CORRELATION AND LOW-RANK FEATURE EXTRACTION

Guo Jiqiang¹, Xu Xudong², Zhang Shuai², Ren Mifeng¹, Wang Fang¹, Yan Gaowei¹

Author information +

文章历史 +

摘要

针对云的动态变化对辐照度的直接影响,基于傅里叶相位相关（PC）理论从连续地基云图获取云的动态信息矩阵（DIM）,为了减小噪声及冗余信息对模型的影响,构建低秩矩阵特征提取（LMFE）模型作为提取模块（EM）,实现DIM有效信息的提取,EM通过迭代训练得到最优特征提取矩阵W和偏置项b。同时,以双向门控循环单元（Bi-GRU）为基础搭建回归模块（RM）,RM共享EM输出W和b,从云图提取的有效信息结合历史辐照度序列作为输入,实现辐照度的多步回归预测。对真实采集的数据进行实验仿真,结果表明该预测方法可有效提高辐照度预测精度。

Abstract

Aiming at the direct impact of dynamic changes of the clouds on irradiance, this paper obtains the cloud dynamic information matrix （DIM） from continuous ground-based cloud images based on the Fourier phase correlation （PC） theory. To minimize the effects on the model led by noise and redundant information, a low-rank matrix feature extraction （LMFE） model is constructed as an extraction module （EM） to extract valid information from the DIM productively. EM obtains the optimal feature extraction matrix W and bias terms b through iteration. Simultaneously, the regression module （RM） is constructed based on the bidirectional gated recurrent unit （Bi-GRU）, where RM shares EM outputs W and b, and the valid information extracted from the cloud images is combined with the historical irradiance sequence as input to achieve multi-step regression prediction of irradiance. The experimental simulation of the actual collected data demonstrates that the prediction method can effectively improve the irradiance prediction accuracy.

导出引用

郭吉强, 徐旭东, 张帅, 任密蜂, 王芳, 阎高伟. 基于云图相位相关和低秩特征提取的超短期辐照度预测[J]. 太阳能学报. 2025, 46(3): 494-503 https://doi.org/10.19912/j.0254-0096.tynxb.2023-1799

Guo Jiqiang, Xu Xudong, Zhang Shuai, Ren Mifeng, Wang Fang, Yan Gaowei. ULTRA-SHORT-TERM IRRADIANCE PREDICTION BASED ON CLOUD IMAGES PHASE CORRELATION AND LOW-RANK FEATURE EXTRACTION[J]. Acta Energiae Solaris Sinica. 2025, 46(3): 494-503 https://doi.org/10.19912/j.0254-0096.tynxb.2023-1799

中图分类号： TM615

参考文献

[1] VERBOIS H, HUVA R, RUSYDI A, et al.Solar irradiance forecasting in the tropics using numerical weather prediction and statistical learning[J]. Solar energy, 2018, 162: 265-277.
[2] 吴凌霄, 王一楠, 旺堆, 等. 西藏羊八井地区太阳短波辐照度特征及其短期预测模型对比分析[J]. 地球物理学报, 2023, 66(8): 3144-3156.
WU L X, WANG Y N, WANGDUI, et al. Study on the characteristics of solar shortwave irradiance and comparative analysis of short-term irradiance prediction of Yangbajing, Tibet[J]. Chinese journal of geophysics, 2023, 66(8): 3144-3156.
[3] 张成, 白建波, 兰康, 等. 基于数据挖掘和遗传小波神经网络的光伏电站发电量预测[J]. 太阳能学报, 2021, 42(3): 375-382.
ZHANG C, BAI J B, LAN K, et al.Photovoltaic power generation prediction based on data mining and genetic wavelet neural network[J]. Acta energiae solaris sinica, 2021, 42(3): 375-382.
[4] SI Z Y, YANG M, YU Y X, et al.Photovoltaic power forecast based on satellite images considering effects of solar position[J]. Applied energy, 2021, 302: 117514.
[5] 余光正, 陆柳, 汤波, 等. 基于云图特征提取的改进混合神经网络超短期光伏功率预测方法[J]. 中国电机工程学报, 2021, 41(20): 6989-7003.
YU G Z, LU L, TANG B, et al.An improved hybrid neural network ultra-short-term photovoltaic power forecasting method based on cloud image feature extraction[J]. Proceedings of the CSEE, 2021, 41(20): 6989-7003.
[6] 张青山, 王丽婕, 郝颖, 等. 基于卫星云图和晴空模型的分布式光伏电站太阳辐照度超短期预测[J]. 高电压技术, 2022, 48(8): 3271-3281.
ZHANG Q S, WANG L J, HAO Y, et al.Ultra-short-term solar irradiance prediction of distributed photovoltaic power stations based on satellite cloud images and clear sky model[J]. High voltage engineering, 2022, 48(8): 3271-3281.
[7] 张臻, 陈天鹏, 王磊, 等. 基于地基云图的超短期太阳辐照预测方法与装置研究[J]. 太阳能学报, 2023, 44(1): 133-140.
ZHANG Z, CHEN T P, WANG L, et al.Research on ultra-short-term solar irradiance prediction method and devicebased on ground-based cloud images[J]. Acta energiae solaris sinica, 2023, 44(1): 133-140.
[8] DONG Z B, YANG D Z, REINDL T, et al.Satellite image analysis and a hybrid ESSS/ANN model to forecast solar irradiance in the tropics[J]. Energy conversion and management, 2014, 79: 66-73.
[9] PALETTA Q, ARBOD G, LASENBY J.Omnivision forecasting: combining satellite and sky images for improved deterministic and probabilistic intra-hour solar energy predictions[J]. Applied energy, 2023, 336: 120818.
[10] FU C L, CHENG H Y.Predicting solar irradiance with all-sky image features via regression[J]. Solar energy, 2013, 97: 537-550.
[11] CHENG H Y, YU C C.Multi-model solar irradiance prediction based on automatic cloud classification[J]. Energy, 2015, 91: 579-587.
[12] WANG Z J, WANG L, HUANG C, et al.A hybrid ensemble learning model for short-term solar irradiance forecasting using historical observations and sky images[J]. IEEE transactions on industry applications, 2023, 59(2): 2041-2049.
[13] YANG H, WANG L, HUANG C, et al.3D-CNN-based sky image feature extraction for short-term global horizontal irradiance forecasting[J]. Water, 2021, 13(13): 1773.
[14] 钟振兴, 马晓波, 安巍. 基于地基云图与气象数据的辐照度轻量化预测[J]. 东北电力大学学报, 2021, 41(1): 24-30.
ZHONG Z X, MA X B, AN W.A lightweight solar irradiance prediction model based on ground-based cloud images and meteorological data[J]. Journal of Northeast Electric Power University, 2021, 41(1): 24-30.
[15] 朱琼锋, 李家腾, 乔骥, 等. 人工智能技术在新能源功率预测的应用及展望[J]. 中国电机工程学报, 2023, 43(8): 3027-3048.
ZHU Q F, LI J T, QIAO J, et al.Application and prospect of artificial intelligence technology in renewable energy forecasting[J]. Proceedings of the CSEE, 2023, 43(8): 3027-3048.
[16] 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.
[17] WEN H R, DU Y, CHEN X Y, et al.Deep learning based multistep solar forecasting for PV ramp-rate control using sky images[J]. IEEE transactions on industrial informatics, 2021, 17(2): 1397-1406.
[18] BERNECKER D, RIESS C, ANGELOPOULOU E, et al.Continuous short-term irradiance forecasts using sky images[J]. Solar energy, 2014, 110: 303-315.
[19] 蒋俊霞, 高晓清, 吕清泉, 等. 基于地基云图的云跟踪与太阳辐照度超短期预报方法研究[J]. 太阳能学报, 2020, 41(5): 351-358.
JIANG J X, GAO X Q, LYU Q Q, et al.Study on cloud tracking and solar irradiance ultra-short-term forecasting based on TSI images[J]. Acta energiae solaris sinica, 2020, 41(5): 351-358.
[20] 刘翼飞, 崔承刚. 基于地基云图云量特征的光伏发电功率区间预测[J]. 南方电网技术, 2023, 17(2): 92-100.
LIU Y F, CUI C G.Interval prediction for short-term solar power based on cloud features of ground-based cloud images[J]. Southern power system technology, 2023, 17(2): 92-100.
[21] 王育飞, 郝德扬, 薛花, 等. 计及云图和混沌特性的光伏功率组合预测方法[J]. 太阳能学报, 2023, 44(12): 74-81.
WANG Y F, HAO D Y, XUE H, et al.Combined forecasting approach of photovoltaic power based on cloud images and chaotic characteristics[J]. Acta energiae solaris sinica, 2023, 44(12): 74-81.
[22] 王飞, 甄钊, 米增强, 等. 基于相位相关的天空图像云团运动速度计算方法研究[J]. 太阳能学报, 2016, 37(10): 2539-2546.
WANG F, ZHEN Z, MI Z Q, et al.Cloud velocity calculation method of sky images based on Fourier phase correlation theory[J]. Acta energiae solaris sinica, 2016, 37(10): 2539-2546.
[23] ZHEN Z, XUAN Z M, WANG F, et al.Image phase shift invariance based multi-transform-fusion method for cloud motion displacement calculation using sky images[J]. Energy conversion and management, 2019, 197: 111853.
[24] ZHEN Z, SUN Y J, WANG F, et al.A cloud displacement estimation approach for sky images based on phase correlation theory[C]//2016 IEEE International Conference on Power System Technology (POWERCON). Wollongong, Australia, 2016: 1-6.
[25] 张雲钦, 程起泽, 蒋文杰, 等. 基于EMD-PCA-LSTM的光伏功率预测模型[J]. 太阳能学报, 2021, 42(9): 62-69.
ZHANG Y Q, CHENG Q Z, JIANG W J, et al.Photovoltaic power prediction model based on EMD-PCA-LSTM[J]. Acta energiae solaris sinica, 2021, 42(9): 62-69.
[26] ZHOU J H, ZHANG Q, ZENG S N, et al.Latent linear discriminant analysis for feature extraction via isometric structural learning[J]. Pattern recognition, 2024, 149: 110218.
[27] 黄冬梅, 张晓桐, 张明华, 等. 全局判别与局部稀疏保持HSI半监督特征提取[J]. 计算机工程与应用, 2019, 55(20): 184-191.
HUANG D M, ZHANG X T, ZHANG M H, et al.Global discriminant and local sparse preserving semi-supervised feature extraction for HSI[J]. Computer engineering and applications, 2019, 55(20): 184-191.
[28] 杨利锋, 林大华, 邓振云, 等. 低秩特征选择多输出回归算法[J]. 计算机工程与应用, 2017, 53(20): 116-121.
YANG L F, LIN D H, DENG Z Y, et al.Low-rank feature selection for multiple-output regression algorithm[J]. Computer engineering and applications, 2017, 53(20): 116-121.
[29] YUAN H L, LI J Y, LAI L L, et al.Low-rank matrix regression for image feature extraction and feature selection[J]. Information sciences, 2020, 522: 214-226.
[30] 李大中, 李颖宇. 基于深度学习与误差修正的超短期风电功率预测[J]. 太阳能学报, 2021, 42(12): 200-205.
LI D Z, LI Y Y.Ultra-short term wind power prediction based on deep learning and error correction[J]. Acta energiae solaris sinica, 2021, 42(12): 200-205.
[31] PEDRO H T C, LARSON D P, COIMBRA C F M. A comprehensive dataset for the accelerated development and benchmarking of solar forecasting methods[J]. 2019, 11(3): 036102.
[32] PARK S, KIM Y, FERRIER N J, et al.Prediction of solar irradiance and photovoltaic solar energy product based on cloud coverage estimation using machine learning methods[J]. Atmosphere, 2021, 12(3): 395.
[33] WEN H R, DU Y, LIM E G, et al.A solar forecasting framework based on federated learning and distributed computing[J]. Building and environment, 2022, 225: 109556.