基于改进块梯法的超短期光伏电站辐照度预测研究

董浩淼; 张耀; 林帆; 李嘉兴; 廖建; 张贝西

doi:10.19912/j.0254-0096.tynxb.2025-0775

PDF(8427 KB)

太阳能学报 ›› 2026, Vol. 47 ›› Issue (9) : 341-351. DOI: 10.19912/j.0254-0096.tynxb.2025-0775

基于改进块梯法的超短期光伏电站辐照度预测研究

董浩淼, 张耀, 林帆, 李嘉兴, 廖建, 张贝西

作者信息 +

STUDY ON ULTRA-SHORT-TERM PHOTOVOLTAIC POWER STATION IRRADIANCE FORECASTING BASED ON IMPROVED BLOCK-LADDER METHOD

Dong Haomiao, Zhang Yao, Lin Fan, Li Jiaxing, Liao Jian, Zhang Beixi

Author information +

文章历史 +

摘要

提出一种基于改进块梯法的超短期光伏电站辐照度预测方法。首先对数据集进行预处理,包括对地基云图进行鱼眼畸变矫正以及对辐照度数据建立晴空模型并生成晴空指数。接着采用基于最小交叉熵的自适应阈值计算方法识别地基云图中的云层,并利用基于相似度加权的云位移矢量计算方法进行云运动预测。最后通过改进块梯法预测光伏发电辐照度。实验在UCSD-Folsom数据集中进行仿真验证,结果表明,该方法有效提高了超短期光伏电站辐照度预测精度并拓展了传统块梯法的预测时段。

Abstract

This paper proposes an ultra-short-term photovoltaic power station irradiance forecasting method based on an improved block-ladder method. Firstly, the dataset is preprocessed, including fisheye distortion correction on ground-based sky images. A clear sky model is established for the irradiance data to generate clear sky indices. Next, clouds in the ground-based sky images are identified using an adaptive threshold calculation method based on minimum cross-entropy, and cloud motion is predicted with a similarity-weighted cloud motion vector calculation method. Finally, ultra-short-term photovoltaic irradiance forecasting is performed using the improved block-ladder method. Experimental results on the UCSD-Folsom dataset show that this method improves forecasting accuracy and extends the forecasting period of the traditional block-ladder method.

导出引用

董浩淼, 张耀, 林帆, 李嘉兴, 廖建, 张贝西. 基于改进块梯法的超短期光伏电站辐照度预测研究[J]. 太阳能学报. 2026, 47(9): 341-351 https://doi.org/10.19912/j.0254-0096.tynxb.2025-0775

Dong Haomiao, Zhang Yao, Lin Fan, Li Jiaxing, Liao Jian, Zhang Beixi. STUDY ON ULTRA-SHORT-TERM PHOTOVOLTAIC POWER STATION IRRADIANCE FORECASTING BASED ON IMPROVED BLOCK-LADDER METHOD[J]. Acta Energiae Solaris Sinica. 2026, 47(9): 341-351 https://doi.org/10.19912/j.0254-0096.tynxb.2025-0775

中图分类号： TM615

参考文献

[1] 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.
[2] 国家能源局. 我国风电光伏发电总装机突破8亿千瓦 [EB/OL].http://www.nea.gov.cn/2023-05/25/c_1310721539.htm.
National Energy Administration.China’s wind and solar power generation capacity exceeds 800 million kilowatts[EB/OL]. http://www.nea.gov.cn/2023-05/25/c_1310721539.htm.
[3] Raza M Q, Nadarajah M, Ekanayake C.On recent advances in PV output power forecast[J]. Solar Energy, 2016, 136: 125-144.
[4] 宋文乐, 张烨, 刘航旭, 等. 基于光伏组件老化特性解耦的渔光互补光伏短期出力预测方法[J]. 电力建设, 2024, 45(7): 25-33.
Song W L, Zhang Y, Liu H X, et al.Short-term output prediction method for complementary fishing and solar power decoupling the aging characteristics of photovoltaic modules[J]. Electric Power Construction, 2024, 45(7): 25-33.
[5] 任密蜂, 王家辉, 叶泽甫, 等. 一种适用于单/多光伏电站的迁移超短期光伏预测建模框架[J]. 太阳能学报, 2024, 45(6): 359-367.
Ren M F, Wang J H, Ye Z F, et al.Transfer ultra-short term photovoltaic prediction modeling framework for single/multiple photovoltaic power stations[J]. Acta Energiae Solaris Sinica, 2024, 45(6): 359-367.
[6] 王舒雨, 李豪, 马刚, 等. 基于TCN和DLinear的光伏发电功率多步预测模型[J]. 电力建设, 2025, 46(4): 173-184.
Wang S Y, Li H, Ma G, et al.Multistep prediction model for photovoltaic power generation based on time convolution and DLinear[J]. Electric Power Construction, 2025, 46(4): 173-184.
[7] Barnes A K, Balda J C, Hayes J K.Modelling PV clouding effects using a semi-Markov process with application to energy storage[J]. IFAC Proceedings Volumes, 2014, 47(3): 9444-9449.
[8] 徐普, 谌颖琪, 宋启明, 等. 风浪流联合作用下 “风力机-光伏-网箱” 浮式综合平台动力响应分析[J]. 太阳能学报, 2025, 46(3): 626-634.
Xu P, Chen Y Q, Song Q M, et al.Dynamic response analysis of “wind turbine-photovoltaic-net cage” floating integrated platform under combined actions of winds, waves and currents[J]. Acta Energiae Solaris Sinica, 2025, 46(3): 626-634.
[9] Du J, Min Q L, Zhang P L, et al.Short-term solar irradiance forecasts using sky images and radiative transfer model[J]. Energies, 2018, 11(5): 1107.
[10] Kamadinata J O, Ken T L, Suwa T.Sky image-based solar irradiance prediction methodologies using artificial neural networks[J]. Renewable Energy, 2019, 134: 837-845.
[11] Cheng H Y.Cloud tracking using clusters of feature points for accurate solar irradiance nowcasting[J]. Renewable Energy, 2017, 104: 281-289.
[12] 苏忠贤, 周建军, 潘玉良. 固定式太阳能光伏板输出功率的若干问题[J]. 机电工程, 2008, 25(12): 31-34.
Su Z X, Zhou J J, Pan Y L.Some output power issues of fixed PV panel[J]. Mechanical & Electrical Engineering Magazine, 2008, 25(12): 31-34.
[13] Lin F, Zhang Y, Wang J X.Recent advances in intra-hour solar forecasting: a review of ground-based sky image methods[J]. International Journal of Forecasting, 2023, 39(1): 244-265.
[14] Peng Z Z, Yu D T, Huang D, et al.3D cloud detection and tracking system for solar forecast using multiple sky imagers[J]. Solar Energy, 2015, 118: 496-519.
[15] Chu Y H, Pedro H T C, Coimbra C F M. Hybrid intra-hour DNI forecasts with sky image processing enhanced by stochastic learning[J]. Solar energy, 2013, 98: 592-603.
[16] Nou J, Chauvin R, Eynard J, et al.Towards the intrahour forecasting of direct normal irradiance using sky-imaging data[J]. Heliyon, 2018, 4(4): e00598.
[17] Ryu A, Ito M, Ishii H, et al.Preliminary analysis of short-term solar irradiance forecasting by using total-sky imager and convolutional neural network[C]//2019 IEEE PES GTD Grand International Conference and Exposition Asia (GTD Asia). Bangkok, Thailand, 2019: 627-631.
[18] Sun Y C, Szűcs G, Brandt A R.Solar PV output prediction from video streams using convolutional neural networks[J]. Energy & Environmental Science, 2018, 11(7): 1811-1818.
[19] 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.
[20] Marquez R, Coimbra C F M. Intra-hour DNI forecasting based on cloud tracking image analysis[J]. Solar Energy, 2013, 91: 327-336.
[21] Chang M C, Yao Y, Li G, et al.Cloud tracking for solar irradiance prediction[C]//2017 IEEE International Conference on Image Processing (ICIP). Beijing, China, 2017: 4387-4391.
[22] Chu Y H, Pedro H T C, Nonnenmacher L, et al. A smart image-based cloud detection system for intrahour solar irradiance forecasts[J]. Journal of Atmospheric and Oceanic Technology, 2014, 31(9): 1995-2007.
[23] Caldas M, Alonso-Suárez R.Very short-term solar irradiance forecast using all-sky imaging and real-time irradiance measurements[J]. Renewable Energy, 2019, 143: 1643-1658.
[24] 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]. Journal of Renewable and Sustainable Energy, 2019, 11(3): 036102.
[25] Mahima, Karakoti I, Pathak P P, et al. A comprehensive study of ground measurement and satellite-derived data of global and diffuse radiation[J]. Environmental Progress & Sustainable Energy, 2019, 38(3): e13060.
[26] NASA Power.NASA power data access viewer[EB/OL]. https://power.larc.nasa.gov/data-access-viewer.
[27] 马金玉, 梁宏, 罗勇, 等. 中国近50年太阳直接辐射和散射辐射变化趋势特征[J]. 物理学报, 2011, 60(6): 853-866.
Ma J Y, Liang H, Luo Y, et al.Variation trend of direct and diffuse radiation in China over recent 50 years[J]. Acta Physica Sinica, 2011, 60(6): 853-866.
[28] Bacher P, Madsen H, Nielsen H A.Online short-term solar power forecasting[J]. Solar Energy, 2009, 83(10): 1772-1783.