A hierarchical approach to probabilistic wind power forecasting

Ciaran Gilbert; Jethro Browell; David McMillan

doi:10.1109/PMAPS.2018.8440571

A hierarchical approach to probabilistic wind power forecasting

Ciaran Gilbert, Jethro Browell, David McMillan

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

4 Citations (Scopus)

35 Downloads (Pure)

Abstract

This paper describes a method to generate improved probabilistic wind farm power forecasts in a hierarchical framework with the incorporation of production data from individual wind turbines. Wind power forms a natural hierarchy as generated electricity is aggregated from the individual turbine, to farm, to the regional level and so on. To forecast the wind farm power generation, a layered approach is proposed whereby deterministic forecasts from the lower layer (turbine level) are used as input features to an upper-level (wind farm) probabilistic model. In a case study at a utility scale wind farm it is shown that improvements in probabilistic forecast skill (CRPS) of 1.24% and 2.39% are obtainable when compared to two very competitive benchmarks based on direct forecasting of the wind farm power using Gradient Boosting Trees and an Analog Ensemble, respectively.

Original language	English
Title of host publication	2018 IEEE International Conference on Probabilistic Methods Applied to Power Systems (PMAPS)
Place of Publication	Piscataway, NJ
Publisher	IEEE
Number of pages	6
ISBN (Print)	9781538635964
DOIs	https://doi.org/10.1109/PMAPS.2018.8440571
Publication status	E-pub ahead of print - 20 Aug 2018
Event	2018 IEEE International Conference on Probabilistic Methods Applied to Power Systems (PMAPS) - Boise, ID, United States Duration: 24 Jun 2018 → 28 Jun 2018

Conference

Conference	2018 IEEE International Conference on Probabilistic Methods Applied to Power Systems (PMAPS)
Country/Territory	United States
Period	24/06/18 → 28/06/18

Keywords

wind power
probabilistic forecasting
hierarchical forecasting
forecasting
wind power integration

Access to Document

10.1109/PMAPS.2018.8440571

Gilbert-etal-PMAPS2018-A-hierarchical-approach-to-probabilistic-wind-power-forecastingAccepted author manuscript, 398 KB

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

4 Citations
1 Article

Leveraging turbine-level data for improved probabilistic wind power forecasting
Gilbert, C., Browell, J. & McMillan, D., 31 Jul 2020, In: IEEE Transactions on Sustainable Energy. 11, 3, p. 1152-1160 9 p.
Research output: Contribution to journal › Article › peer-review

Open Access
File
49 Citations (Scopus)

83 Downloads (Pure)

Cite this

@inproceedings{715a9d34df98415e925b14e5a3b622f1,

title = "A hierarchical approach to probabilistic wind power forecasting",

abstract = "This paper describes a method to generate improved probabilistic wind farm power forecasts in a hierarchical framework with the incorporation of production data from individual wind turbines. Wind power forms a natural hierarchy as generated electricity is aggregated from the individual turbine, to farm, to the regional level and so on. To forecast the wind farm power generation, a layered approach is proposed whereby deterministic forecasts from the lower layer (turbine level) are used as input features to an upper-level (wind farm) probabilistic model. In a case study at a utility scale wind farm it is shown that improvements in probabilistic forecast skill (CRPS) of 1.24% and 2.39% are obtainable when compared to two very competitive benchmarks based on direct forecasting of the wind farm power using Gradient Boosting Trees and an Analog Ensemble, respectively.",

keywords = "wind power, probabilistic forecasting, hierarchical forecasting, forecasting, wind power integration",

author = "Ciaran Gilbert and Jethro Browell and David McMillan",

note = "{\textcopyright} 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.; 2018 IEEE International Conference on Probabilistic Methods Applied to Power Systems (PMAPS) ; Conference date: 24-06-2018 Through 28-06-2018",

year = "2018",

month = aug,

day = "20",

doi = "10.1109/PMAPS.2018.8440571",

language = "English",

isbn = "9781538635964",

booktitle = "2018 IEEE International Conference on Probabilistic Methods Applied to Power Systems (PMAPS)",

publisher = "IEEE",

}

Gilbert, C, Browell, J & McMillan, D 2018, A hierarchical approach to probabilistic wind power forecasting. in 2018 IEEE International Conference on Probabilistic Methods Applied to Power Systems (PMAPS). IEEE, Piscataway, NJ, 2018 IEEE International Conference on Probabilistic Methods Applied to Power Systems (PMAPS), United States, 24/06/18. https://doi.org/10.1109/PMAPS.2018.8440571

TY - GEN

T1 - A hierarchical approach to probabilistic wind power forecasting

AU - Gilbert, Ciaran

AU - Browell, Jethro

AU - McMillan, David

N1 - © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2018/8/20

Y1 - 2018/8/20

N2 - This paper describes a method to generate improved probabilistic wind farm power forecasts in a hierarchical framework with the incorporation of production data from individual wind turbines. Wind power forms a natural hierarchy as generated electricity is aggregated from the individual turbine, to farm, to the regional level and so on. To forecast the wind farm power generation, a layered approach is proposed whereby deterministic forecasts from the lower layer (turbine level) are used as input features to an upper-level (wind farm) probabilistic model. In a case study at a utility scale wind farm it is shown that improvements in probabilistic forecast skill (CRPS) of 1.24% and 2.39% are obtainable when compared to two very competitive benchmarks based on direct forecasting of the wind farm power using Gradient Boosting Trees and an Analog Ensemble, respectively.

AB - This paper describes a method to generate improved probabilistic wind farm power forecasts in a hierarchical framework with the incorporation of production data from individual wind turbines. Wind power forms a natural hierarchy as generated electricity is aggregated from the individual turbine, to farm, to the regional level and so on. To forecast the wind farm power generation, a layered approach is proposed whereby deterministic forecasts from the lower layer (turbine level) are used as input features to an upper-level (wind farm) probabilistic model. In a case study at a utility scale wind farm it is shown that improvements in probabilistic forecast skill (CRPS) of 1.24% and 2.39% are obtainable when compared to two very competitive benchmarks based on direct forecasting of the wind farm power using Gradient Boosting Trees and an Analog Ensemble, respectively.

KW - wind power

KW - probabilistic forecasting

KW - hierarchical forecasting

KW - forecasting

KW - wind power integration

U2 - 10.1109/PMAPS.2018.8440571

DO - 10.1109/PMAPS.2018.8440571

M3 - Conference contribution book

SN - 9781538635964

BT - 2018 IEEE International Conference on Probabilistic Methods Applied to Power Systems (PMAPS)

PB - IEEE

CY - Piscataway, NJ

T2 - 2018 IEEE International Conference on Probabilistic Methods Applied to Power Systems (PMAPS)

Y2 - 24 June 2018 through 28 June 2018

ER -

A hierarchical approach to probabilistic wind power forecasting

Abstract

Conference

Keywords

Access to Document

Fingerprint

Projects

EPSRC Centre for Doctoral Training in Wind & Marine Energy Systems | Gilbert, Ciaran

Research output

Leveraging turbine-level data for improved probabilistic wind power forecasting

Cite this