The decaying prices and improving efficiency of bifacial solar photovoltaic (PV) technologies make them most promising for harnessing solar radiation. Deserts have a high solar potential, but harsh conditions like high temperatures and dust negatively affect the performance of any proposed solar system. The most attractive aspect of deserts is their long-term sustainability, as they are free from urban and agricultural expansion. In this work, the System Advisor Model (SAM) software version 2023.12.17 was used to model a 100 MW PV plant and evaluate the techno-economic performance of fixed, 1-axis, and 2-axis bifacial systems under the climatic conditions of six deserts from around the world. This study explores technical parameters such as the performance ratio, specific yield, and capacity factor. Additionally, the levelized cost of energy (LCOE) indicator was used to compare the economic performance of the different systems. Results showed high specific yield: the averages for the three systems in six deserts were 2040, 2372, and 2555 kWh/kWp, respectively. Economic analysis found that an LCOE below 4 ¢/kWh is achievable in all deserts, reaching a minimum of 2.45 ¢/kWh under favorable conditions. These results emphasize the high potential of utility-scale PV projects in deserts to advance a green, sustainable energy future.

This study presents a computationally efficient stacked ensemble model for daily photovoltaic energy prediction. The ensemble combines five base regressors, including extreme gradient boosting, decision trees, random forests, neural networks, and k-nearest neighbors. A weighted linear combination merges these outputs, with weights optimized through differential evolution. The proposed method is evaluated against Bayesian optimization and equal-weighted ensembles, focusing on prediction accuracy and specific optimizer computational costs. While Bayesian optimization is widely used in solar forecasting, results show that differential evolution outperforms it with a root mean square error of 77.019 kWh and a coefficient of determination of 96.215% while converging in as few as 30 iterations. In contrast, Bayesian optimization plateaued without improvement after 100 iterations and incurred 31 to 121 times higher optimizer overhead than differential evolution. This highlights the superior scalability of differential evolution, particularly as the computational cost of Gaussian process-based updates increases with sample size. Seasonal evaluation shows highest accuracy in winter, and validation using external data confirms the generalizability of the method. Overall, the results demonstrate that differential evolution remains a robust and scalable solution for big-data solar energy prediction applications.

Agrivoltaics—the co-location of photovoltaic energy production with agriculture—offers a promising pathway to address growing pressures on land, food, and clean energy resources. This study evaluates the first agrivoltaic pilot installation in Jordan, located in Amman (935 m above sea level; hot-summer Mediterranean climate), during its first operational year. Two 11.1 kWp bifacial photovoltaic (PV) systems were compared: (i) a south-facing array tilted at 10°, and (ii) a vertical east–west “fence” configuration. The tilted system achieved an annual specific yield of 1962 kWh/kWp, approximately 35% higher than the 1288 kWh/kWp obtained from the vertical array. Seasonal variation was observed, with the performance gap widening to ~45% during winter and narrowing to ~22% in June. As expected, the vertical system exhibited more uniform diurnal output, enhanced early-morning and late-afternoon generation, and lower soiling losses. The light profiles measured for the year indicate that vertical systems barely impede the light requirements of crops, while the tilted system splits into distinct profiles for the intra-row area (akin to the vertical system) and sub-panel area, which is likely to support only low-light requirement crops. This configuration increases the levelized cost of electricity (LCOE) by roughly 88% compared to a conventional ground-mounted system due to elevated structural costs. In contrast, the vertical east–west system provides an energy yield equivalent to about 33% of the land area at the tested configuration but achieves this without increasing the LCOE. These results highlight a fundamental trade-off: elevated tilted systems offer greater land-use efficiency but at higher cost, whereas vertical systems preserve cost parity at the expense of lower energy density.