提出一种基于深度模糊神经网络的太阳总辐射预测模型。首先利用Pearson相关系数分析太阳总辐射关键影响因素,其次利用深度学习多隐含层所具有的特征提取优势将模糊神经网络模块重复连接,构建深度模糊神经网络模型,并使用蝗虫优化算法对其中心值和宽度进行优化。利用所提太阳总辐射预测模型对5个气象站点的相关数据进行仿真实验,并对结果进行分析。仿真结果表明：所提预测模型较其他模型具有较高的预测精度,验证了模型的有效性,可满足无辐射监测站点太阳总辐射预测的需要。
Abstract
This paper proposes a global solar radiation forecast model based on deep fuzzy neural network. Firstly, Pearson correlation coefficient is used to analyze key influence factors of global solar radiation. Then, the fuzzy neural network modules are repeatedly connected to construct a deep fuzzy neural network model by using the feature extraction advantage of deep learning multiple hidden layers. Moreover, the width and center value of the membership function in this model are optimized by the grasshopper optimization algorithm. Finally, simulation experiments are conducted by using the proposed global solar radiation forecast model based on related data of five meteorological sites. The simulation results show that the proposed model has higher forecast accuracy than other models, and verifies the validity of the model, which meets the requirements of global solar radiation forecast at some sites without radiation monitoring.
关键词
太阳能 /
太阳辐射 /
预测 /
深度模糊神经网络 /
蝗虫优化算法
Key words
solar energy /
solar radiation /
forecasting /
deep fuzzy neural network /
grasshopper optimization algorithm
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 王建平, 谢云林, 朱程辉, 等. 基于相空间重构小波神经网络的太阳逐日辐射能量预测[J]. 太阳能学报, 2013, 34(9): 1651-1655.
WANG J P, XIE Y L, ZHU C H, et al.Daily solar radiation prediction based on phase space reconstruction of wavelet neural network[J]. Acta energiae solaris sinica, 2013, 34(9): 1651-1655.
[2] 倪超, 王聪, 朱婷婷, 等. 基于CNN-Bi-LSTM的太阳辐照度超短期预测[J]. 太阳能学报, 2022, 43(3): 197-202.
NI C, WANG C, ZHU T T, et al.Super-short-term forecast of solar irradiance based on CNN-Bi-LSTM[J]. Acta energiae solaris sinica, 2022, 43(3): 197-202.
[3] 田翠霞, 黄敏, 朱启兵. 基于EMD-LMD-LSSVM联合模型的逐时太阳辐照度预测[J]. 太阳能学报, 2018, 39(2): 504-512.
TIAN C X, HUANG M, ZHU Q B.Hourly solar irradiance forecast based on EMD-LMD-LSSVM joint model[J]. Acta energiae solaris sinica, 2018, 39(2): 504-512.
[4] 黄海静, 张京红, 覃文娜, 等. 基于小波神经网络法的海南地区逐时太阳总辐射预测研究[J]. 气象与环境学报, 2016, 32(1): 60-65.
HUANG H J, ZHANG J H, QIN W N, et al.Forecast of hourly total solar radiation based on a wavelet back propagation neural network method in Hainan Province[J]. Journal of meteorology and environment, 2016, 32(1): 60-65.
[5] ÁLVAREZ-ALVARADO J M, RÍOS-MORENO J G, OBREGÓN-BIOSCA S A, et al. Hybrid techniques to predict solar radiation using support vector machine and search optimization algorithms: a review[J]. Applied sciences, 2021, 11(3): 1044.
[6] ZHANG L, MA W P, ZHANG D.Stacked sparse autoencoder in PolSAR data classification using local spatial information[J]. IEEE geoscience and remote sensing letters, 2016, 13(9): 1359-1363.
[7] HINTON G E, SALAKHUTDINOV R R.Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507.
[8] YUN S H, DO KOO Y, NA M.Collapse moment estimation for wall-thinned pipe bends and elbows using deep fuzzy neural networks[J]. Nuclear engineering and technology, 2020, 52(11): 2678-2685.
[9] SAREMI S, MIRJALILI S, LEWIS A.Grasshopper optimisation algorithm: theory and application[J]. Advances in engineering software, 2017, 105: 30-47.
[10] HERSBACH H, BELL B, BERRISFORD P, et al. ERA5 hourly data on single levels from1979 to present[EB/OL]. Copernicus Climate Change Service (C3S) Climate Data Store (CDS). 10.24381/cds.adbb2d47.
[11] RIETVELD M R.A new method for estimating the regression coefficients in the formula relating solar radiation to sunshine[J]. Agricultural meteorology, 1978, 19(2/3): 243-252.
[12] 冯姣姣, 王维真, 李净, 等. 基于BP神经网络的华东地区太阳辐射模拟及时空变化分析[J]. 遥感技术与应用, 2018, 33(5): 881-889, 955.
FENG J J, WANG W Z, LI J, et al.Simulation of solar radiation based on BP neural network and its spatio-temporal change analysis in East China[J]. Remote sensing technology and application, 2018, 33(5): 881-889, 955.
[13] 李净, 王卫东, 张福存. 利用LM-BP神经网络估算西北地区太阳辐射[J]. 干旱区地理, 2015, 38(3): 438-445.
LI J, WANG W D, ZHANG F C.Simulation of solar radiation in northwest China based on LM-BP neural network[J]. Arid land geography, 2015, 38(3): 438-445.
基金
国家自然科学基金青年项目（11705135）; 陕西省自然科学基础研究计划项目（2020JM-573）; 西安工程大学博士科研启动基金（BS1339）
PDF(3627 KB)
