File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/TSTE.2021.3124228
- Scopus: eid_2-s2.0-85118607765
- WOS: WOS:000772458800054
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Online Ensemble Approach for Probabilistic Wind Power Forecasting
Title | Online Ensemble Approach for Probabilistic Wind Power Forecasting |
---|---|
Authors | |
Keywords | Wind power forecasting Probabilistic forecasting Online learning Ensemble learning Quantile regression Passive-aggressive regression |
Issue Date | 2021 |
Citation | IEEE Transactions on Sustainable Energy, 2021 How to Cite? |
Abstract | Probabilistic wind power forecasting is an important input in the decision-making process in future electric power grids with large penetrations of renewable generation. Traditional probabilistic wind power forecasting models are trained offline and are then used to make predictions online. However, this strategy cannot make full use of the most recent information during the prediction process. In addition, ensemble learning is recognized as an effective approach for further improving forecasting performance by combining multiple forecasting models. This paper studies an online ensemble approach for probabilistic wind power forecasting by taking full advantage of the most recent information and leveraging the strengths of multiple forecasting models. The online ensemble approach is first formulated as an online convex optimization model. On this basis, a quantile passive-aggressive regression model is proposed to solve the online convex optimization model. Case studies and comparisons with other online learning methods are conducted on an open wind power data set from Belgium. Results show that the proposed method outperforms competing methods in terms of pinball loss and Winkler score with high reliability. |
Persistent Identifier | http://hdl.handle.net/10722/308682 |
ISSN | 2023 Impact Factor: 8.6 2023 SCImago Journal Rankings: 4.364 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Von Krannichfeldt, Leandro | - |
dc.contributor.author | Wang, Yi | - |
dc.contributor.author | Zufferey, Thierry | - |
dc.contributor.author | Hug, Gabriela | - |
dc.date.accessioned | 2021-12-08T07:49:54Z | - |
dc.date.available | 2021-12-08T07:49:54Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | IEEE Transactions on Sustainable Energy, 2021 | - |
dc.identifier.issn | 1949-3029 | - |
dc.identifier.uri | http://hdl.handle.net/10722/308682 | - |
dc.description.abstract | Probabilistic wind power forecasting is an important input in the decision-making process in future electric power grids with large penetrations of renewable generation. Traditional probabilistic wind power forecasting models are trained offline and are then used to make predictions online. However, this strategy cannot make full use of the most recent information during the prediction process. In addition, ensemble learning is recognized as an effective approach for further improving forecasting performance by combining multiple forecasting models. This paper studies an online ensemble approach for probabilistic wind power forecasting by taking full advantage of the most recent information and leveraging the strengths of multiple forecasting models. The online ensemble approach is first formulated as an online convex optimization model. On this basis, a quantile passive-aggressive regression model is proposed to solve the online convex optimization model. Case studies and comparisons with other online learning methods are conducted on an open wind power data set from Belgium. Results show that the proposed method outperforms competing methods in terms of pinball loss and Winkler score with high reliability. | - |
dc.language | eng | - |
dc.relation.ispartof | IEEE Transactions on Sustainable Energy | - |
dc.subject | Wind power forecasting | - |
dc.subject | Probabilistic forecasting | - |
dc.subject | Online learning | - |
dc.subject | Ensemble learning | - |
dc.subject | Quantile regression | - |
dc.subject | Passive-aggressive regression | - |
dc.title | Online Ensemble Approach for Probabilistic Wind Power Forecasting | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/TSTE.2021.3124228 | - |
dc.identifier.scopus | eid_2-s2.0-85118607765 | - |
dc.identifier.eissn | 1949-3037 | - |
dc.identifier.isi | WOS:000772458800054 | - |