Integrated Spatiotemporal Hybrid Solar PV Generation Forecast Between Countries on Different Continents Using Transfer Learning Method

Abstract

Solar photovoltaic (PV) generation is a cornerstone of sustainable energy production, but predicting its capacity across countries remains challenging due to factors like climate, terrain, and population density. To address this, a recent study proposed a novel approach using transfer learning, which is particularly valuable when historical data for newly established PV plants is limited. The study evaluated four PV plants in South Korea and Germany, selected for their diverse geographical and climatic conditions. The proposed CL-Transformer model outperformed established machine learning models such as LSTM, CNN-LSTM, and Transformer, consistently demonstrating superior predictive capabilities. Notably, when trained on Korean data and applied to both South Korea and Germany, the model achieved an average R $^{2}_{\mathrm {adj}}$ improvement of 23.5 %. When trained on German data, the improvement was even more pronounced at 67.3 %. Additionally, transfer learning experiments revealed up to a 50.6 % enhancement in R $^{2}_{\mathrm {adj}}$ across different plant scales. By integrating external weather variables and satellite data, this hybrid model provides valuable insights for accurate capacity prediction and strategic planning in deploying new PV plants, contributing to greater stability and efficiency in the power industry.

Keywords

• Geostationary satellite
• photovoltaics
• region of interest extraction
• spatiotemporal
• transfer learning