Estimation of hourly global solar radiation using artificial neural network in Adana province, Turkey
1Department of Mechanical Engineering, Adana Alparslan Turkes Science and Technology University, Adana, Turkey
2Department of Electrical and Electronics Engineering, Adana Alparslan Turkes Science and Technology University, Adana, Turkey
J Ther Eng 2021; 7(8): 2017-2030 DOI: 10.18186/thermal.1051313
Full Text PDF


Since global solar radiation (GSR) is an important parameter for the design, installation, and operation of solar energy-based systems, it is important to have precise information about it. As the indicating devices are expensive and their requirements such as operation and maintenance should be carried out, the measurement of solar radiation cannot be frequently taken. On the other hand, the measurements of different meteorological parameters such as relative humidity, sunshine duration, and ground surface temperature are more prevalent in meteorology stations. Therefore, the estimation of solar radiation is a significant parameter for the areas where the measurements could not be performed and to complete the missing information in databases. Many different models, software, and simulation programs are utilized to calculate solar radiation data, provide an economic advantage, and obtain high accuracy. The main purpose of this study is to perform an estimation of solar radiation in Adana, where is on the east of the Mediterranean in Turkey, by using an artificial neural network (ANN) model. The best estimation performance is obtained by optimizing the neuron numbers used in the network’s hidden layer with the trial and error method. With this aim, hourly data including wind speed, wind direction, humidity, sunshine duration, actual pressure, and average temperature are taken as inputs while solar radiation is taken as a target. All these data, which is for 2018, has taken from the Turkish State Meteorological Service. A linear correlation coefficient value has been obtained to be about 0.87313 with the mean square error (MSE) of 1.6184x104 W/m2 for the testing data set. The ANN’s testing/validation results show that it has a low MSE, indicating the accuracy and adequacy of the network model. Besides, the predicted ANN output is evaluated to be remarkably close to the measured target data by considering the linear correlation coefficient.