Conference paper
Adaptive Generalized Logit-Normal Distributions for Wind Power Short-Term Forecasting
Department of Electrical Engineering, Technical University of Denmark1
Center for Electric Power and Energy, Centers, Technical University of Denmark2
Energy Analytics and Markets, Center for Electric Power and Energy, Centers, Technical University of Denmark3
Operations Research, Management Science, Department of Technology, Management and Economics, Technical University of Denmark4
Management Science, Department of Technology, Management and Economics, Technical University of Denmark5
Department of Technology, Management and Economics, Technical University of Denmark6
There is increasing interest in very short-term and higher-resolution wind power forecasting (from mins to hours ahead), especially offshore. Statistical methods are of utmost relevance, since weather forecasts cannot be informative for those lead times. Those approaches ought to account for the fact wind power generation as a stochastic process is non-stationary, double-bounded (by zero and the nominal power of the turbine) and non-linear.
Accommodating those aspects may lead to improving both point and probabilistic forecasts. We propose to focus on generalized logit-normal distributions, which are naturally suitable and flexible for double-bounded and non-linear processes. Relevant parameters are estimated via maximum likelihood inference.
Both batch and online versions of the estimation approach are described - the online version permitting to additionally handle non-stationarity through parameter variation. The approach is applied and analysed on the test case of the Anholt offshore wind farm in Denmark, with emphasis placed on 10-min-ahead forecasting.
| Language: | English |
|---|---|
| Publisher: | IEEE |
| Year: | 2021 |
| Pages: | 1-6 |
| Proceedings: | 2021 IEEE Madrid PowerTech |
| ISBN: | 1665435976 and 9781665435970 |
| Types: | Conference paper |
| DOI: | 10.1109/PowerTech46648.2021.9494900 |
| ORCIDs: | Pierrot, Amandine and Pinson, Pierre |
10-min-ahead forecasting Adaptation models Anholt offshore wind farm Maximum likelihood estimation Predictive models Probabilistic logic Upper bound Wind farms Wind power generation adaptive generalized logit-normal distributions double-bounded processes higher-resolution wind power forecasting lead times load forecasting log normal distribution maximum likelihood estimation nominal power nonlinear processes offshore installations online versions probabilistic forecasts statistical methods stochastic process stochastic processes weather forecasts wind power wind power generation wind power plants wind power short-term forecasting
