Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
11004976 | International Journal of Forecasting | 2018 | 12 Pages |
Abstract
We provide probabilistic forecasts of photovoltaic (PV) production, for several PV plants located in France up to 6 days of lead time, with a 30-min timestep. First, we derive multiple forecasts from numerical weather predictions (ECMWF and Météo France), including ensemble forecasts. Second, our parameter-free online learning technique generates a weighted combination of the production forecasts for each PV plant. The weights are computed sequentially before each forecast using only past information. Our strategy is to minimize the Continuous Ranked Probability Score (CRPS). We show that our technique provides forecast improvements for both deterministic and probabilistic evaluation tools.
Related Topics
Social Sciences and Humanities
Business, Management and Accounting
Business and International Management
Authors
J. Thorey, C. Chaussin, V. Mallet,