Machine learning and analytical model hybridization to assess the impact of climate change on solar PV energy production

Abstract

The United Nations' (UN) Sustainable Development Goals (SDGs) agenda has triggered numerous countries to harness solar energy from solar photovoltaic (PV) modules to increase the share of renewable energy in the global energy mix. However, geographical and climatic factors have a significant impact on the electrical performance of solar PV modules. In addition, since solar PV energy production models are the only physics-based approach to transferring ground-measured PV energy production to other locations, the authors developed 294 physical models from six different PV power technologies and validated them for the model's adaptability. To facilitate the possible determination of PV electric energy generation in the unique geographical and climatic environment of the experiment site, these models were built using machine learning, Gumbel's probabilistic approach (GPM), and hybridization of the two. The major challenges in this study are in developing the hybridized machine learning with the Gumbel probabilistic functional model, which resides in the mathematical transformation process, which required a great deal of repeated mathematical science knowledge to arrive at the final transformed and efficient model for predicting the potential of solar PV output. With a thorough coefficient of determination (R2) of 0.9998% and a root mean square error (RMSE) of 0.0063 kwh, the hybrid model with only the measurable solar radiation parameter is the closest to the measured PV energy production of all technologies. The best hybridized model was used to explore the potential impacts of climate change on the different solar PV technologies. This was achieved by using energy parameters from the Australian Community Climate and Global System Simulation (ACCESS-CM2) in Phase 6. On an annual basis, the effects of climate change on various PV technologies have had a small adverse impact (less than 1%) on these renewable energy technologies. It was also found that, compared to other technologies, CIGS thin film technology produced the least negative effects on climate change, with 10.94%–36.75% in the best-case, 35.71%–36.36% in the moderate-case, and 33.33–40.00% in the worst-case scenario for shared socioeconomic pathways (SSP126, SSP245, and SSP585) emissions. This suggests the intrinsic properties of Copper Indium Gallium Selenide (CIGS) thin film modules are more effective at withstanding high temperatures as they contribute 60.00–89.66% of their intrinsic module properties to PV energy production compared to other technologies. However, taking into account the time, resource availability, cost-effectiveness, commercialization, and consumption of various PV technologies studied in this era of global sustainability, poly-crystalline (p-Si) technology is highly recommended for harvesting solar PV energy products in Alice Springs, Australia.