Dimensions overall score 4.0

GitHub Code Pulse

No public code linked for this paper yet.

• SHADECast is the most reliable model for PV power forecasting, achieving a CRPS 10.8% lower than SolarSTEPS at a two-hour lead time.result 95%
• State-of-the-art nowcasting models struggle to capture solar ramp dynamics, with forecast RMSE increasing by up to 50% compared to normal operating conditions.limitation 95%
• Ramp-up events are typically associated with cloud dissipation during the morning, while ramp-down events commonly occur when cloud cover increases in the afternoon.result 90%
• The study analyzes two years of PV power production from 6434 PV stations at 15-minute resolution.method 95%
• The study uses a spatiotemporal forecasting framework to evaluate deterministic and probabilistic PV power forecasts from deep learning and physics-based models.method 90%
• Most PV installations in the study are located in the Swiss Plateau or in valleys within the Alpine region.technical 85%
• The predicted irradiance fields are converted into PV power using station-specific machine learning models.method 90%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card