Projects per year
Abstract
This paper describes two methods for creating improved probabilistic wind power forecasts through the use of turbine-level data. The first is a feature engineering approach whereby deterministic power forecasts from the turbine level are used as explanatory variables in a wind farm level forecasting model. The second is a novel bottom-up hierarchical approach where the wind farm forecast is inferred from the joint predictive distribution of the power output from individual turbines. Notably, the latter produces probabilistic forecasts that are coherent across both turbine and farm levels, which the former does not. The methods are tested at two utility scale wind farms and are shown to provide consistent improvements of up to 5%, in terms of continuous ranked probability score compared to the best performing state-of-the-art benchmark model. The bottom-up hierarchical approach provides greater improvement at the site characterized by a complex layout and terrain, while both approaches perform similarly at the second location. We show that there is a clear benefit in leveraging readily available turbine-level information for wind power forecasting.
Original language | English |
---|---|
Pages (from-to) | 1152-1160 |
Number of pages | 9 |
Journal | IEEE Transactions on Sustainable Energy |
Volume | 11 |
Issue number | 3 |
Early online date | 6 Jun 2019 |
DOIs | |
Publication status | Published - 31 Jul 2020 |
Keywords
- wind power forecasting
- turbine-level data
- wind farm
Fingerprint
Dive into the research topics of 'Leveraging turbine-level data for improved probabilistic wind power forecasting'. Together they form a unique fingerprint.Projects
- 1 Finished
-
EPSRC Centre for Doctoral Training in Wind & Marine Energy Systems | Gilbert, Ciaran
Browell, J. (Principal Investigator), McMillan, D. (Co-investigator) & Gilbert, C. (Research Co-investigator)
EPSRC (Engineering and Physical Sciences Research Council)
1/10/15 → 28/06/21
Project: Research Studentship - Internally Allocated
Datasets
-
Supplementary Material for: "Leveraging Turbine-level Data for Improved Probabilistic Wind Power Forecasting" (Revised)
Gilbert, C. (Creator), Browell, J. (Creator) & McMillan, D. (Creator), University of Strathclyde, 23 May 2019
DOI: 10.15129/6b949176-4608-430c-b13c-b201afb921c4
Dataset
-
Supplementary Material for: "Leveraging Turbine-level Data for Improved Probabilistic Wind Power Forecasting"
Gilbert, C. (Creator), Browell, J. (Creator) & McMillan, D. (Creator), University of Strathclyde, 2018
DOI: 10.15129/16283615-65e4-402d-8fe6-cc9916e37a74
Dataset
Research output
- 51 Citations
- 1 Conference contribution book
-
A hierarchical approach to probabilistic wind power forecasting
Gilbert, C., Browell, J. & McMillan, D., 20 Aug 2018, (E-pub ahead of print) 2018 IEEE International Conference on Probabilistic Methods Applied to Power Systems (PMAPS). Piscataway, NJ: IEEE, 6 p.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book
Open AccessFile4 Citations (Scopus)38 Downloads (Pure)
Activities
- 1 Invited talk
-
System-wide Probabilistic Energy Forecasting
Browell, J. (Speaker)
28 Apr 2020Activity: Talk or presentation types › Invited talk