EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Spatiotemporal Downscaling Model for Solar Irradiance Forecast Using Nearest-Neighbor Random Forest and Gaussian Process

Shadrack Asiedu, Abhilasha Suvedi, Zongjie Wang, Hossein Rekabdarkolaee, Timothy Hansen

Energies · 10.05.2025 · 18 (10) · 2447

DOI: 10.3390/en18102447 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Energies, online erschienen am 10.05.2025. Verfasst von Shadrack Asiedu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: SDSU Richard McComish, Ph.D. Fellowship in Energy Infrastructure, U.S. Department of Energy Office of Science, Office of Electricity Microgrid R&D Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate solar photovoltaic (PV) capacity estimation requires high-resolution, site-specific solar irradiance data to account for localized variability. However, global datasets, such as the National Solar Radiation Database (NSRDB), provide regional averages that fail to capture the fine-scale fluctuations critical for large-scale grid integration. This limitation is particularly relevant in the context of increasing distributed energy resources (DERs) penetration, such as rooftop PV. Additionally, it is critical to the implementation of the U.S. Federal Energy Regulatory Commission (FERC) Order 2222, which facilitates DER participation in U.S. bulk power markets. To address this challenge, this study evaluates Nearest-Neighbor Random Forest (NNRF) and Nearest-Neighbor Gaussian Process (NNGP) models for spatiotemporal downscaling of global solar irradiance data. By leveraging historical irradiance and meteorological data, these models incorporate spatial, temporal, and feature-based correlations to enhance local irradiance predictions. The NNRF model, a machine-learning approach, prioritizes computational efficiency and predictive accuracy, while the NNGP model offers a level of interpretability and prediction uncertainty by numerically quantifying correlations and dependencies in the data. Model validation was conducted using day-ahead predictions. The results showed that the average Goodness of Fit (GoF) of the NNRF model of 90.61% across all eight sites outperformed the GoF of the NNGP of 85.88%. Additionally, the computational speed of NNRF was 2.5 times faster than the NNGP. Finally, the NNGP displayed polynomial scaling while the NNRF scaled linearly with increasing number of nearest neighbors. Additional validation of the model on five sites in Puerto Rico further confirmed the superiority of the NNRF model over the NNGP model. These findings highlight the robustness and computational efficiency of NNRF for large-scale solar irradiance downscaling, making it a strong candidate for improving PV capacity estimation and real-time electricity market integration for DERs.

Förderung

  • SDSU Richard McComish, Ph.D. Fellowship in Energy Infrastructure
  • U.S. Department of Energy Office of Science
  • Office of Electricity Microgrid R&D Program
  • Office of Energy Efficiency and Renewable Energy Solar Energy Technology Office
  • U.S. National Science Foundation

Zitieren

APA

Asiedu, S., Suvedi, A., Wang, Z., Rekabdarkolaee, H., & Hansen, T. (2025). Spatiotemporal Downscaling Model for Solar Irradiance Forecast Using Nearest-Neighbor Random Forest and Gaussian Process. Energies, 18(10), 2447. https://doi.org/10.3390/en18102447

Vancouver

Asiedu S, Suvedi A, Wang Z, Rekabdarkolaee H, Hansen T. Spatiotemporal Downscaling Model for Solar Irradiance Forecast Using Nearest-Neighbor Random Forest and Gaussian Process. Energies. 2025;18(10):2447. doi:10.3390/en18102447

BibTeX
@article{Asiedu2025,
  author = {Asiedu, Shadrack and Suvedi, Abhilasha and Wang, Zongjie and Rekabdarkolaee, Hossein and Hansen, Timothy},
  title = {Spatiotemporal Downscaling Model for Solar Irradiance Forecast Using Nearest-Neighbor Random Forest and Gaussian Process},
  journal = {Energies},
  year = {2025},
  volume = {18},
  number = {10},
  pages = {2447},
  doi = {10.3390/en18102447}
}
Kostenlos starten →