Solar Radiation Ramping Events Modeling Using Spatio-Temporal Point Processes

The accurate modeling and prediction of solar ramping events are critical for enhancing the situational awareness of solar power generation systems. The impact of weather conditions, including temperature, humidity, and cloud density, on the emergence and position of solar ramping events is well acknowledged. In addition, abnormal ramping events are typically strongly correlated in space and time, posing a challenge for modeling these events with complex spatio-temporal correlations. To address this challenge, we propose a novel spatio-temporal categorical point process model that effectively addresses the correlation and interaction among ramping events. Through extensive real-data experiments, we demonstrate the interpretability and predictive power of our model. History: Bianca Maria Colosimo served as the senior editor for this article. Funding: C. Xu, M. Zhang, and Y. Xie were partially supported by the National Science Foundation (NSF) [Grants CCF-1650913, DMS-1938106, DMS-1830210, and CMMI-2015787]. Additional support from the NSF [Grants DMS-2134037 and CMMI-2112533] is gratefully acknowledged. Data Ethics & Reproducibility Note: The code capsule is available on Code Ocean at https://codeocean.com/capsule/7597817/tree/v1 and in the e-Companion to this article (available at https://doi.org/10.1287/ijds.2023.0006 ).