基于GRU-RF模型的太阳辐照度短时预测

周满国; 黄艳国; 段锦锋

doi:10.19912/j.0254-0096.tynxb.2020-1091

PDF(2095 KB)

太阳能学报 ›› 2022, Vol. 43 ›› Issue (7) : 166-173. DOI: 10.19912/j.0254-0096.tynxb.2020-1091

基于GRU-RF模型的太阳辐照度短时预测

周满国, 黄艳国, 段锦锋

作者信息 +

SHORT TERM PREDICTION OF SORAL IRRADIANCE BASED ON GRU-RF MODEL

Zhou Manguo, Huang Yanguo, Duan Jinfeng

Author information +

文章历史 +

摘要

针对现有太阳辐照度短期预测方法的建模复杂、准确度低等问题,提出一种基于深度学习的GRU-RF动态权值组合预测方法。大气因素与太阳辐照度数据融合,将运算速度较快且模型复杂度较低的随机森林（RF）模型与带有时序记忆的门控循环单元（GRU）神经网络进行动态权值的加权集成,分别将地表接收到的太阳辐照度、近地层气温、相对湿度、近地层风速和相对气压等变化特征进行预测研究。通过几种模型对比分析,结果表明使用GRU-RF模型预测短时（9 h）太阳辐照度结果较好,运行速度较快,在不同时间间隔（5、10以及15 min）下能够很好地预测太阳辐照度数据。

Abstract

Aiming at the problems of complex modeling and low accuracy of existing short-term solar irradiance prediction methods, a GRU-RF dynamic weight combination prediction method based on deep learning is proposed. The atmospheric factors and solar irradiance data are fused, and the random forest （RF） model with fast operation speed and low model complexity is integrated with the gated recurrent unit （GRU） neural network with time sequence memory for dynamic weight weighting. The variation characteristics of solar irradiance, surface air temperature, relative humidity, surface wind speed and relative pressure received by the surface are predicted respectively. Through the comparison and analysis of several models, the results show that the GRU-RF model can be used to predict the solar irradiance in short time （9 h） with faster running speed, and can be used to predict the solar irradiance data well in different time intervals （5,10 and 15 min）.

导出引用

周满国, 黄艳国, 段锦锋. 基于GRU-RF模型的太阳辐照度短时预测[J]. 太阳能学报. 2022, 43(7): 166-173 https://doi.org/10.19912/j.0254-0096.tynxb.2020-1091

Zhou Manguo, Huang Yanguo, Duan Jinfeng. SHORT TERM PREDICTION OF SORAL IRRADIANCE BASED ON GRU-RF MODEL[J]. Acta Energiae Solaris Sinica. 2022, 43(7): 166-173 https://doi.org/10.19912/j.0254-0096.tynxb.2020-1091

中图分类号： TK513.5

参考文献

[1] SUN H W, ZHAO N, ZENG X F, et al.Study of solar radiation prediction and modeling of relationships between solar radiation and meteorological variables[J]. Energy conversion and management, 2015, 105: 880-890.
[2] TAHER M, AHLEM H, SOUHEIL E A, et al.A novel solar concentrating system based on a fixed cylindrical reflector and tracking receiver[J]. Renewable energy, 2018, 117: 85-107.
[3] STJERN C W, KRISTJÁNSSON J E, HANSEN A W. Global dimming and global brightening-An analysis of surface radiation and cloud cover data in northern Europe[J]. International journal of climatology, 2009, 29(5): 643-653.
[4] YANG X, JIANG F, LIU H.Short-term power prediction of photovoltaic plant based on SVM with similar data and wavelet analysis[J]. Przegląd elektrotechniczny, 2013, 89(5): 81-85.
[5] CHAABENE M, AMMAR M B.Neuro-fuzzy dynamic model with Kalman filter to forecast irradiance and temperature for solar energy systems[J]. Renewable energy, 2008, 33(7): 1435-1443.
[6] HAMMER A, HEINEMANN D, LORENZ E, et al.Short-term forecasting of solar radiation; a statistical approach using satellite data[J]. Solar energy, 1999, 67(1/3): 139-150.
[7] MELLIT A, PAVAN A M.A 24-h forecast of solar irradiance using artificial neural network; Application for performance prediction of a grid-connected PV plant at Trieste, Italy[J]. Solar energy, 2010, 84(5): 807-821.
[8] MARQUEZ R, COIMBRA C F M. Forecasting of global and direct solar irradiance using stochastic learning methods, ground experiments and the NWS database[J]. Solar energy, 2011, 85(5): 746-756.
[9] WILD M, FOLINI D, HENSCHEL F, et al.Projections of long-term changes in solar radiation based on CMIP5 climate models and their influence on energy yields of photovoltaic systems[J]. Solar energy, 2015, 116: 12-24.
[10] PARIDA B, INIYAN S, GOIC R.A review of solar photovoltaic technologies[J]. Renewable & sustainable energy reviews, 2011, 15(3): 1625-1636.
[11] MARZO A, TRIGO-GONZALEZ M, ALONSO-MONTESINOS J, et al.Daily global solar radiation estimation in desert areas using daily extreme temperatures and extraterrestrial radiation[J]. Renewable energy, 2017, 113: 303-311.
[12] HASSAN M A, KHALIL A, KASEB S, et al.Independent models for estimation of daily global solar radiation:A review and a case study[J]. Renewable and sustainable energy reviews, 2018, 82: 1565-1575.
[13] WU Y X, GUO T T, WANG H.Photovoltaic power prediction method based on similar day and BP neutral network[J]. Top conference series:earth and environmental science, 2018, 170(4):042016 .
[14] 张立影, 孟令甲, 王泽忠. 基于双层BP神经网络的光伏电站输出功率预测[J]. 电测与仪表, 2015, 52(11): 31-35.
ZHANG L Y, MENG L J, WANG Z Z.Photovoltaic power station output power prediction based on the double BP neural network[J]. Electrical measurement & instrumentation, 2015, 52(11): 31-35.
[15] 张玉, 莫寒, 张烈平. 基于模糊支持向量机的光伏发电量预测[J]. 热力发电, 2017, 46(1): 116-120.
ZHANG Y, MO H, ZHAGN L P.Photovoltaic power prediction based on fuzzy support vector machine[J]. Thermal power generation, 2017, 46(1): 116-120.
[16] 余飞鸿, 陈永强, 雷霞, 等. 基于模糊聚类和组合预测算法的光伏短期预测[J]. 计算机仿真, 2019, 36(2): 447-451.
YU F H, CHEN Y Q, LEI X, et al.Short-term prediction of photovoltaic output based on meteorological data fuzzy clustering and GAPS-BP algorithm[J]. Computer simulation, 2019, 36(2): 447-451.
[17] 王恩宇, 郭强, 张学友, 等. 倾斜面太阳辐射量计算方法研究[J]. 热科学与技术, 2019, 18(1): 35-41.
WANG E Y, GUO Q, ZHANG X Y, et al.A study of methods to calculate the solar radiation on inclined surfaces[J]. Journal of thermal science and technology, 2019, 18(1): 35-41.
[18] 陈杰, 张新燕, 吕光建. 基于小波包神经网络的太阳逐时辐射预测[J]. 电测与仪表, 2016, 53(17): 49-54.
CHEGN J, ZHANG X Y, LYU G J.Study on prediction of solar radiation intensity based on wavelet decomposition and BP neural network[J]. Electrical measurement & instrumentation, 2016, 53(17): 49-54.
[19] CHO K, VAN MERRIENBOER B, GULCEHRE C, et al.Learning phrase representations using RNN encoder-decoder for statistical machine translation[J]. Association for Computational Linguistics, 2014, 14(1): 1724-1734.
[20] 刘剑, 曹美燕, 高治军,等. 一种基于随机森林的太阳能辐射预测模型[J]. 控制工程, 2017, 24(12): 2472-2477.
LIU J, CAO M Y, GAO Z J, et al.A solar radiation prediction model based on random forest[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar, 2014.
[21] ZHAO H, GALLO O, FROSIO I, et al.Loss functions for image restoration with neural networks[J]. IEEE transactions on computational imaging, 2017, 3(1): 47-57.