Modelling Hourly Global Horizontal Irradiance from Satellite-Derived Datasets and Climate Variables as New Inputs with Artificial Neural Networks
Modelling Hourly Global Horizontal Irradiance from Satellite-Derived Datasets and Climate Variables as New Inputs with Artificial Neural Networks
复制标题
DOI：
10.3390/en12010148
复制
发表时间：
2019-01
期刊：
影响因子：
3.2
通讯作者：
Bikhtiyar Ameen;H. Balzter;C. Jarvis;J. Wheeler
中科院分区：
文献类型：
--
作者：
Bikhtiyar Ameen;H. Balzter;C. Jarvis;J. Wheeler
在地面测量有限的地区，太阳能领域需要更准确的每小时全球水平辐照度 (GHI) 数据。该研究的目的是通过使用卫星衍生数据集 (SDD) 的新输入、水平表面晴空 (Cs) 和大气层顶部 (TOA) 辐照度的新输入组合以及观测到的气候变量，即日照时长 (SD)、气温 (AT)、相对湿度 (RH) 和风速 (WS)，获得更精确的每小时 GHI。使用 Levenberg-Marquardt 训练算法将变量放置在十个不同的集合中作为人工神经网络中的模型，以获得训练、验证和测试数据的结果。它已应用于伊拉克东北部的两种类型的站。四个自动站的所有变量的新输入组合（r = 0.983、RMSE = 9.5% 和偏差 = 0.0%）改善了观察到的输入变量（相关系数 (r) = 0.755、均方根误差 (RMSE) = 33.7% 和偏差 = 0.3%）的测试数据结果。同样，他们在没有记录 SD 的 5 个塔台站也得到了改进（从：r = 0.601、RMSE = 41% 和偏差 = 0.7% 到：r = 0.976、RMSE = 11.2% 和偏差 = 0.0%）。通过使用新的输入，每小时 GHI 的估算略有增强。
More accurate data of hourly Global Horizontal Irradiance (GHI) are required in the field of solar energy in areas with limited ground measurements. The aim of the research was to obtain more precise and accurate hourly GHI by using new input from Satellite-Derived Datasets (SDDs) with new input combinations of clear sky (Cs) and top-of-atmosphere (TOA) irradiance on the horizontal surface and with observed climate variables, namely Sunshine Duration (SD), Air Temperature (AT), Relative Humidity (RH) and Wind Speed (WS). The variables were placed in ten different sets as models in an artificial neural network with the Levenberg–Marquardt training algorithm to obtain results from training, validation and test data. It was applied at two station types in northeast Iraq. The test data results with observed input variables (correlation coefficient (r) = 0.755, Root Mean Square Error (RMSE) = 33.7% and bias = 0.3%) are improved with new input combinations for all variables (r = 0.983, RMSE = 9.5% and bias = 0.0%) at four automatic stations. Similarly, they improved at five tower stations with no recorded SD (from: r = 0.601, RMSE = 41% and bias = 0.7% to: r = 0.976, RMSE = 11.2% and bias = 0.0%). The estimation of hourly GHI is slightly enhanced by using the new inputs.