The global agenda to increase the renewable energy share has driven many countries and entities to harness solar energy from solar photovoltaic (PV) systems. However, the power generation of PV systems is strongly affected by climate conditions. Therefore, the main objective of this study is to analyze and predict the power generation of different PV technologies under arid desert climate conditions on an hourly basis. Two areas have been considered as case studies: Adrar in Algeria and Alice Springs in Australia. A total of nine physical models and input parameter combinations from six different power plants have been used and tested for the suitability of the proposed models for predicting the power yield of PV power plants depending on solar irradiance and other meteorological variables. Then, an ensemble learning technique is applied to improve the performance capabilities of the best-fit input combinations. The results reveal that the global irradiance, ambient air temperature, and relative humidity combination are the most related to the PV power output of all technologies under all-sky conditions and provide effective and efficient performance with the proposed ensemble learning, with an estimated accuracy of over 99%.

This research was designed to apply measured and theoretically derived models to estimate the optimal tilt angle (β), maximum incident solar radiation (H_T), and global radiation index (GRI) in Lagos and 37 metropolitan cities in Nigeria. Six modules were mounted at different tilt angles with two modules north-facing, three south-facing, and one positioned horizontally to determine the orientation and tilt angle performance. Overall, the 16.8° module 4 south-facing tilted emerged as the best performing module for H_T, with maximum output power, and much more than 6.174 annual earned energy reported on module 6 mounted horizontally. The GRI obtained from the six solar modules revealed a significant coefficient of 1.0269 for module 1 north-facing, 0.9923 for module 2 north-facing, 1.0217 for module 3 south-facing, 0.9609 for module 4 south-facing, and 1.0232 for module 5 south-facing for the values obtained from the horizontally positioned module 6. In-depth statistical analysis of the effectiveness of values observed against the predicted values to estimate the optimal and maximum inclination angle of incident solar radiation using error metrics and GPI revealed that model 5, model 12, model 14, model 17, and model 14 outperform the other estimation models in their respective categories. A similar statistical analysis of model 14 with the best performance was performed to estimate the best inclination angle in 37 metropolitan cities in Nigeria compared to two models consolidated in the literature; model 14 performed admirably in terms of accuracy compared to the two models obtained from the literature.