Global solar radiation can theoretically be approximated in terms of tilt and azimuth of the surface regarding the impossibility of simultaneous measurement of solar radiation at various surface tilt and azimuth angles. Moreover, the random and anisotropic nature of diffuse radiation in a tropical climate makes it extremely difficult to estimate global solar radiation accurately as a function of surface tilt and azimuth angles. This study aims to develop a novel experimental and theoretical approach in the form of a computational network in order to determine a precise combined model integrated with global horizontal solar radiation to evaluate global tilted solar radiation in a tropical climate. Obtained results revealed that precisely estimation of the global tilted solar radiation was possible, by combining geometric factors for the tilted beam solar radiation, a combination of Gueymard and Louche models for the tilted diffuse solar radiation, and isotropic ground reflectance model for the ground reflected radiation, along with global horizontal solar radiation. It was observed that the accuracy of the model developed was higher for the partly sunny sky compared to the cloudy and rainy sky, estimates were more accurate on south-facing surfaces, and the model's accuracy declined with the increasing tilt angle of the surface. The statistical analysis exhibited excellent agreement between the measured data and simulation results, considering the value of normalized mean absolute error (nMAE %), normalized root mean squared error (nRMSE %), and mean absolute percentage error (MAPE %), which were in the ranges 0.22-0.94, 0.27-1.11, and 0.23-1.02, respectively for estimating global tilted solar radiation in various regions of Peninsular Malaysia, and they were respectively found in the range of 10.2-27.5%, 16.1-38.9%, and 6.0-17.8%, for evaluating the monthly optimum tilt angle towards the south, that leads to a loss of solar energy from 1.3 to 5.4 kWh/m2/year in Peninsular Malaysia. This search revealed that the experimental and theoretical approach employed in this study can be extended to more climatic regions.
Solar irradiation data is essential for the feasibility of solar energy projects. Notably, the intermittent nature of solar irradiation influences solar energy use in all forms, whether energy or agriculture. Accurate solar irradiation prediction is the only solution to effectively use solar energy in different forms. The estimation of solar irradiation is the most critical factor for site selection and sizing of solar energy projects and for selecting a suitable crop selection for the area. But the physical measurement of solar irradiation, due to the cost and technology involved, is not possible for all locations across the globe. Numerous techniques have been implemented to predict solar irradiation for this purpose. The two types of approaches that are most frequently employed are empirical techniques and artificial intelligence (AI). Both approaches have demonstrated good accuracy in various places of the world. To find out the best method, a thorough review of research articles discussing solar irradiation prediction has been done to compare different methods for solar irradiation prediction. In this paper, articles predicting solar irradiation using AI and empirical published from 2017 to 2022 have been reviewed, and both methods have been compared. The review showed that AI methods are more accurate than empirical methods. In empirical models, modified sunshine-based models (MSSM) have the highest accuracy, followed by sunshine-based (SSM) and non-sunshine-based models (NSM). The NSM has a little lower accuracy than MSSM and SSM, but the NSM can give good results in sunshine data unavailability. Also, the literature review confirmed that simple empirical models could predict accurately, and increasing the empirical model's polynomial order cannot improve results. Artificial neural networks (ANN) and Hybrid models have the highest accuracy among AI methods, followed by support vector machine (SVM) and adaptive neuro-fuzzy inference system (ANFIS). The increase in efficiency by hybrid models is minimal, but the complexity of models requires very sophisticated programming knowledge. ANN's most important input factors are maximum and minimum temperatures, temperature differential, relative humidity, clearness index and precipitation.