基于GA-BP神经网络的逐时总辐射分组模型研究

于瑛; 陈笑; 贾晓宇; 杨柳

doi:10.19912/j.0254-0096.tynxb.2021-0015

PDF(2020 KB)

太阳能学报 ›› 2022, Vol. 43 ›› Issue (8) : 157-163. DOI: 10.19912/j.0254-0096.tynxb.2021-0015

基于GA-BP神经网络的逐时总辐射分组模型研究

于瑛¹, 陈笑¹, 贾晓宇¹, 杨柳²

作者信息 +

RESEARCH ON GROUPING MODEL OF HOURLY GLOBAL SOLAR RADIATION BASED ON GA-BP NEURAL NETWORK

Yu Ying¹, Chen Xiao¹, Jia Xiaoyu¹, Yang Liu²

Author information +

文章历史 +

摘要

通过分析影响太阳辐射的主要因素,提出以太阳高度角、季节和天气（晴空指数）作为数据划分依据的分组模型建立方法。以拉萨和西安地区的逐时气象数据和辐射数据为例,基于遗传算法（genetic algorithm,GA）优化的BP神经网络,建立太阳高度角、季节和天气类型的逐时总辐射分组模型。该研究揭示分组模型误差变化的规律,并将其估算误差与AllData模型比较。结果显示,相较于AllData模型,分组模型的估算误差均有降低。其中,天气分组模型误差最小,且西安的天气分组模型结果优于拉萨。西安天气分组模型平均绝对百分比误差（MAPE）和相对均方根误差（rRMSE）相较AllData模型结果分别下降3.96%和4.18%。研究结果表明分组模型能够降低逐时总辐射估算误差,可为估算逐时总辐射提供方法借鉴。

Abstract

By analyzing the main factors affecting solar radiation, this paper proposes a grouping modeling method, which uses the solar altitude angle, season and clearness index as the indicators of data classification. The hourly meteorological data and radiation data for Lhasa and Xi'an are selected as examples. The hourly global radiation grouping models for solar altitude, seasons and weather are established respectively through BP neural network optimized by genetic algorithm （GA）. The error variation rules of grouping model are revealed. The error of grouping models are compared with that of the AllData model further. The results show that the estimation error of the grouping model is reduced compared with the AllData model, and the estimation error of the weather grouping model is the smallest. The results of Xi'an's weather grouping model are better than those of Lhasa. Compared with the AllData model, the mean absolute percentage error （MAPE） and relative root mean square error （rRMSE） of Xi'an's weather grouping model is decreased by 3.96% and 4.18%, respectively. The results show that the grouping model can reduce the estimation error of hourly global solar radiation, and provide a reference for neural network as a method for estimating hourly global solar radiation.

导出引用

于瑛, 陈笑, 贾晓宇, 杨柳. 基于GA-BP神经网络的逐时总辐射分组模型研究[J]. 太阳能学报. 2022, 43(8): 157-163 https://doi.org/10.19912/j.0254-0096.tynxb.2021-0015

Yu Ying, Chen Xiao, Jia Xiaoyu, Yang Liu. RESEARCH ON GROUPING MODEL OF HOURLY GLOBAL SOLAR RADIATION BASED ON GA-BP NEURAL NETWORK[J]. Acta Energiae Solaris Sinica. 2022, 43(8): 157-163 https://doi.org/10.19912/j.0254-0096.tynxb.2021-0015

中图分类号： TU119+.2

参考文献

[1] 刘衍, 陈睿昕, 张沫岩, 等. 绿色住区设计参数对太阳辐射的影响研究[J]. 工业建筑, 2020, 50(7): 143-150.
LIU Y, CHEN R X, ZHANG M Y, et al.Research on the influence of green settlement design parameters on solar radiation[J]. Industrial construction, 2020, 50(7): 143-150.
[2] 曹其梦, 于瑛, 杨柳. 太阳逐时总辐射计算模型适用性分析——以我国部分地区为例[J]. 太阳能学报, 2018, 39(4): 917-924.
CAO Q M, YU Y, YANG L.Applicability analysis of hourly total solar radiation calculation model—taking some regions of China as example[J]. Acta energiae solaris sinica, 2018, 39(4): 917-924.
[3] 何知衡, 董浩, 王磊. 太阳辐射影响下的建筑经济保温厚度计算方法[J]. 干旱区资源与环境, 2019, 33(9): 108-115.
HE Z H, DONG J, WANG L.Study on the method for calculation of building economic insulation thickness under the influence of solar radiation[J]. Journal of arid land resources and environment, 2019, 33(9): 108-115.
[4] 朱叶青, 周军莉, 王乾坤. 建筑方案设计中的太阳辐射模拟研究[J]. 建筑节能, 2016, 44(9): 30-33, 83.
ZHU Y Q, ZHOU J L, WANG Q K.Simulation on solar radiation in building design[J]. Building energy efficiency, 2016, 44(9): 30-33, 83.
[5] 赵康, 桂雪晨, 葛坚. 高大空间中太阳辐射对热舒适的影响及室内参数设计[J]. 太阳能学报, 2019, 40(9): 2655-2662.
ZHAO K, GUI X C, GE J.Influence of solar radiation on thermal comfort in large spaces and corresponding design of indoor parameters[J]. Acta energiae solaris sinica, 2019, 40(9): 2655-2662.
[6] ZANG H, XU Q, BIAN H.Generation of typical solar radiation data for different climates of China[J]. Energy, 2012, 38(1): 236-248.
[7] LOGHMARI I, TIMOUMI Y, MESSADI A.Performance comparison of two global solar radiation models for spatial interpolation purposes[J]. Renewable and sustainable energy reviews, 2018, 82(1): 837-844.
[8] MEFTI A, ADANE A, BOUROUBI M Y.Satellite approach based on cloud cover classification: Estimation of hourly global solar radiation from meteosat images[J]. Energy conversion and management, 2008, 49(4): 652-659.
[9] JANJAI S, LAKSANABOONSONG J, NUNEZ M, et al.Development of a method for generating operational solar radiation maps from satellite data for a tropical environment[J]. Solar energy, 2005, 78(6): 739-751.
[10] MUNEER T, YOUNES S.The all-sky meteorological radiation model: proposed improvements[J]. Applied energy, 2006, 83(5): 436-450.
[11] WHILLIER A.The determination of hourly values of total solar radiation from daily summations[J]. Archiv Für meteorologie geophysik und bioklimatologie serie B, 1956, 7(2): 197-204.
[12] JAIN P C.Comparison of techniques for the estimation of daily global irradiation and a new technique for the estimation of hourly global irradiation[J]. Solar & wind technology, 1984, 1(2): 123-134.
[13] NEWELL T A.Simple models for hourly to daily radiation ratio correlations[J]. Solar energy, 1983, 31(3): 339-342.
[14] IBRAHIM I A, KHATIB T.A novel hybrid model for hourly global solar radiation prediction using random forests technique and firefly algorithm[J]. Energy conversion & management, 2017, 138(15): 413-425.
[15] KHATIB T, ELMENREICH W.A model for hourly solar radiation data generation from daily solar radiation data using a generalized regression artificial neural network[J]. International journal of photoenergy, 2015(3): 1-13.
[16] RUIZ L C, AMAYA D, RAMOS O L.Prediction of solar radiation through the anfis lgorithm[J]. Applied mechanics and materials, 2016, 823: 389-395.
[17] CHEN J, LI G.Evaluation of support vector machine for estimation of solar radiation from measured meteorological variables[J]. Theoretical and applied climatology, 2014, 115(3): 627-638.
[18] WANG Z, TIAN C, ZHU Q, et al.Hourly solar radiation forecasting using a Volterra-least squares support vector machine model combined with signal decomposition[J]. Energies, 2018, 11(1): 68.
[19] HASSAN M A, KHALIL A, KASEB S, et al.Exploring the potential of tree-based ensemble methods in solar radiation modeling[J]. Applied energy, 2017, 203: 897-916.
[20] YANG M Q, WANG X Y.Hourly solar radiation forecast based on k-NN nonparametric regression model[J]. Applied mechanics & materials, 2014, 571: 217-222.
[21] HUSSAIN S, ALALILI A.A hybrid solar radiation modeling approach using wavelet multiresolution analysis and artificial neural networks[J]. Applied energy, 2017, 208: 540-550.
[22] GASTóN-ROMEO M, LEON T, MALLOR F, et al. A morphological clustering method for daily solar radiation curves[J]. Solar energy, 2011, 85(9): 1824-1836.
[23] KOO C, LI W, CHA S H, et al.A novel estimation approach for the solar radiation potential with its complex spatial pattern via machine-learning techniques[J]. Renewable energy, 2019, 133: 575-592.
[24] GABALLA H, CHO S.Prediction of hourly solar radiation using temperature and humidity for real-time building energy simulation[J]. Journal of physics conference series, 2019, 1343(1): 012049.
[25] JALLAL M A, CHABAA S, ZEROUAL A.A new artificial multi-neural approach to estimate the hourly global solar radiation in a semi-arid climate site[J]. Theoretical and applied climatology, 2020, 139(3): 1261-1276.
[26] LI D H W, CHEN W, LI S, et al. Estimation of hourly global solar radiation using Multivariate Adaptive Regression Spline (MARS)-a case study of Hong Kong[J]. Energy, 2019, 186(1): 115857.
[27] 曹双华, 曹家枞. 太阳逐时总辐射混沌优化神经网络预测模型研究[J]. 太阳能学报, 2006, 27(2): 164-169.
CAO S H, CAO J Z.Study of chaos optimization neural networks for the forecast of hourly total solar irradiation[J]. Acta energiae solaris sinica, 2006, 27(2): 164-169.
[28] 成驰, 陈正洪, 张礼平, 等. 神经网络模型在逐时太阳辐射预测中应用[J]. 太阳能, 2012(3): 30-33.
CHENG C, CHEN Z H, ZHANG L P, et al.Application of neural network model in hourly solar radiation prediction[J]. Solar energy, 2012(3): 30-33.
[29] 刘大龙, 刘加平, 杨柳, 等. 以晴空指数为主要依据的太阳辐射分区[J]. 建筑科学, 2007(6): 9-11.
LIU D L, LIU J P, YANG L, et al.Clearness index based solar radiation distribution[J]. Building science, 2007(6): 9-11.
[30] 于瑛, 杨柳, 霍旭杰, 等. 日总辐射推算模型在中国的适用性研究[J]. 太阳能学报, 2018, 39(9): 2523-2529.
YU Y, YANG L, HU X J, et al.Analysis of daily global radiation estimation models applicability in China[J]. Acta energiae solaris sinica, 2018, 39(9): 2523-2529.
[31] YOUNES S, CLAYWELL R, MUNEER T.Quality control of solar radiation data: Present status and proposed new approaches[J]. Energy, 2005, 30(9): 1533-1549.
[32] POSADILLO R, LUQUE R L.Hourly distributions of the diffuse fraction of global solar irradiation in Córdoba(Spain)[J]. Energy conversion and management, 2009, 50(2): 223-231.
[33] 蒙炤臻, 林奕桐, 李仕强, 等. 自动站温度、雨量数据的质量控制方法和应用研究[J]. 气象研究与应用, 2014, 35(1): 99-103.
MENG Z Z, LIN Y T, LI S Q, et al.Quality control method and application research for temperature and rainfall data of automatic station[J]. Journal of meteorological research and application, 2014, 35(1): 99-103.
[34] 陈明. MATLAB神经网络原理与实例精解[M]. 北京: 清华大学出版社, 2013.
CHEN M.The principle and example of MATLAB neural network[M]. Beijing: Tsinghua University Press, 2013.
[35] 贾红, 张仁祖, 张佩, 等. 逐时太阳辐照度气候学预报模型研究[J]. 江苏农业科学, 2020, 48(11): 275-281.
JIA H, ZHANG R Z, ZHANG P, et al.Study on climatological prediction model of hourly solar irradiance[J]. Jiangsu agricultural sciences, 2020, 48(11): 275-281.
[36] 姚万祥, 李峥嵘, 李翠, 等. 各种天气状况下太阳辐射照度与太阳光照度关系[J]. 同济大学学报(自然科学版), 2013, 41(5): 784-787.
YAO W X, LI Z R, LI C, et al.Relationship between bolar radiance and solar illuminance under all sky types[J]. Journal of Tongji University (natural science), 2013, 41(5): 784-787.