Coherent Probabilistic Solar Power Forecasting

Conference · Fri Jun 01 04:00:00 EDT 2018 · 2018 IEEE International Conference on Probabilistic Methods Applied to Power Systems (PMAPS)

DOI:https://doi.org/10.1109/pmaps.2018.8440483· OSTI ID:1820913

Panamtash, Hossein ^[1]; Zhou, Qun

---

1. University of central Florida

Solar power has been growing rapidly in recent years. Many countries have invested in solar energy technology, especially in Photovoltaic (PV) power generation. With the increased penetration level, solar power forecasting becomes more challenging. To cope with solar power uncertainties, probabilistic forecasting provides more information than traditional point forecasting. Moreover, multiple PV sites with spatial-temporal correlations need to be taken into account. To produce probabilistic forecasts, this paper applies quantile regression on top of time series models. Considering the coherency among multiple PV sites, a reconciliation is applied using a copula-based bottom-up method or proportion-based top-down method. Numerical results show that the proposed methods efficiently produce accurate and coherent probabilistic solar power forecasts.

• Research Organization: University of central Florida
• Sponsoring Organization: USDOE
• DOE Contract Number: EE0007998; EE0007327
• OSTI ID: 1820913
• Conference Information: Journal Name: 2018 IEEE International Conference on Probabilistic Methods Applied to Power Systems (PMAPS)
• Country of Publication: United States
• Language: English

Related Subjects

quantile regression
coherency
hierarchical probabilistic forecasting
solar power forecasting
time series modeling