Abstract
A framework for assessing the performance of short-term solar forecasting is presented in conjunction with a range of numerical results using global horizontal irradiation (GHI) from the open-source Surface Radiation Budget (SURFRAD) data network. A suite of popular machine learning algorithms is compared according to a set of statistically distinct metrics and benchmarked against the persistence-of-cloudiness forecast and a cloud motion forecast. Results show significant improvement compared to the benchmarks with trade-offs among the machine learning algorithms depending on the desired error metric. Training inputs include time series observations of GHI for a history of years, historical weather and atmospheric measurements, and corresponding date and time stamps such that training sensitivities might be inferred. Prediction outputs are GHI forecasts for 1, 2, 3, and 4 hours ahead of the issue time, and they are made for every month of the year for 7 locations. Photovoltaic power and energy outputs can then be made using the solar forecasts to better understand power system impacts.
Original language | American English |
---|---|
Number of pages | 8 |
State | Published - 2017 |
Event | International Workshop on the Integration of Solar Power into Power Systems (Solar Integration Workshop) - Berlin, Germany Duration: 24 Oct 2017 → 26 Oct 2017 |
Conference
Conference | International Workshop on the Integration of Solar Power into Power Systems (Solar Integration Workshop) |
---|---|
City | Berlin, Germany |
Period | 24/10/17 → 26/10/17 |
NREL Publication Number
- NREL/CP-5D00-70030
Keywords
- machine learning
- solar forecasting
- solar power forecasting
- SURFRAD