The impact of power curve estimation on commercial wind power forecasts - An empirical analysis

Gianni Goretti; Aidan Duffy; Tek Tjing Lie

doi:10.1109/EEM.2017.7981885

The impact of power curve estimation on commercial wind power forecasts - An empirical analysis

Gianni Goretti
, Aidan Duffy
, Tek Tjing Lie

School of Transport and Civil Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

An increasing number of utilities participating in the energy market require short term (i.e. up to 48 hours) power forecasts for renewable generation in order to optimize technical and financial performances. As a result, a large number of forecast providers now operate in the marketplace, each using different methods and offering a wide range of services. This paper assesses five different day-ahead wind power forecasts generated by various service providers currently operating in the market, and compares their performance against the state-of-the-art of short-term wind power forecasting. The work focuses on how power curve estimations can introduce systematic errors that affect overall forecast performance. The results of the study highlight the importance of: accurately modelling the wind speed-to-power output relationships at higher wind speeds; taking account of power curve trends when training models; and the need to incorporate long-term (months to years) power curve variability into the forecast updating process.

Original language	English
Title of host publication	2017 14th International Conference on the European Energy Market, EEM 2017
Publisher	IEEE Computer Society
ISBN (Electronic)	9781509054992
DOIs	https://doi.org/10.1109/EEM.2017.7981885
Publication status	Published - 14 Jul 2017
Event	14th International Conference on the European Energy Market, EEM 2017 - Dresden, Germany Duration: 6 Jun 2017 → 9 Jun 2017

Publication series

Name	International Conference on the European Energy Market, EEM
ISSN (Print)	2165-4077
ISSN (Electronic)	2165-4093

Conference

Conference	14th International Conference on the European Energy Market, EEM 2017
Country/Territory	Germany
City	Dresden
Period	6/06/17 → 9/06/17

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Forecast assessment
Short-term forecasting
Wind energy
Wind power forecast
Wind turbine power curve

Access to Document

10.1109/EEM.2017.7981885

https://arrow.tudublin.ie/engschcivcon/97Licence: CC BY-NC-SA

Cite this

@inproceedings{4e0bc193525542829340c72c2fe830c1,

title = "The impact of power curve estimation on commercial wind power forecasts - An empirical analysis",

abstract = "An increasing number of utilities participating in the energy market require short term (i.e. up to 48 hours) power forecasts for renewable generation in order to optimize technical and financial performances. As a result, a large number of forecast providers now operate in the marketplace, each using different methods and offering a wide range of services. This paper assesses five different day-ahead wind power forecasts generated by various service providers currently operating in the market, and compares their performance against the state-of-the-art of short-term wind power forecasting. The work focuses on how power curve estimations can introduce systematic errors that affect overall forecast performance. The results of the study highlight the importance of: accurately modelling the wind speed-to-power output relationships at higher wind speeds; taking account of power curve trends when training models; and the need to incorporate long-term (months to years) power curve variability into the forecast updating process.",

keywords = "Forecast assessment, Short-term forecasting, Wind energy, Wind power forecast, Wind turbine power curve",

author = "Gianni Goretti and Aidan Duffy and Lie, \{Tek Tjing\}",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 14th International Conference on the European Energy Market, EEM 2017 ; Conference date: 06-06-2017 Through 09-06-2017",

year = "2017",

month = jul,

day = "14",

doi = "10.1109/EEM.2017.7981885",

language = "English",

series = "International Conference on the European Energy Market, EEM",

publisher = "IEEE Computer Society",

booktitle = "2017 14th International Conference on the European Energy Market, EEM 2017",

address = "United States",

}

Goretti, G, Duffy, A & Lie, TT 2017, The impact of power curve estimation on commercial wind power forecasts - An empirical analysis. in 2017 14th International Conference on the European Energy Market, EEM 2017., 7981885, International Conference on the European Energy Market, EEM, IEEE Computer Society, 14th International Conference on the European Energy Market, EEM 2017, Dresden, Germany, 6/06/17. https://doi.org/10.1109/EEM.2017.7981885

The impact of power curve estimation on commercial wind power forecasts - An empirical analysis. / Goretti, Gianni; Duffy, Aidan; Lie, Tek Tjing.
2017 14th International Conference on the European Energy Market, EEM 2017. IEEE Computer Society, 2017. 7981885 (International Conference on the European Energy Market, EEM).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - The impact of power curve estimation on commercial wind power forecasts - An empirical analysis

AU - Goretti, Gianni

AU - Duffy, Aidan

AU - Lie, Tek Tjing

PY - 2017/7/14

Y1 - 2017/7/14

N2 - An increasing number of utilities participating in the energy market require short term (i.e. up to 48 hours) power forecasts for renewable generation in order to optimize technical and financial performances. As a result, a large number of forecast providers now operate in the marketplace, each using different methods and offering a wide range of services. This paper assesses five different day-ahead wind power forecasts generated by various service providers currently operating in the market, and compares their performance against the state-of-the-art of short-term wind power forecasting. The work focuses on how power curve estimations can introduce systematic errors that affect overall forecast performance. The results of the study highlight the importance of: accurately modelling the wind speed-to-power output relationships at higher wind speeds; taking account of power curve trends when training models; and the need to incorporate long-term (months to years) power curve variability into the forecast updating process.

AB - An increasing number of utilities participating in the energy market require short term (i.e. up to 48 hours) power forecasts for renewable generation in order to optimize technical and financial performances. As a result, a large number of forecast providers now operate in the marketplace, each using different methods and offering a wide range of services. This paper assesses five different day-ahead wind power forecasts generated by various service providers currently operating in the market, and compares their performance against the state-of-the-art of short-term wind power forecasting. The work focuses on how power curve estimations can introduce systematic errors that affect overall forecast performance. The results of the study highlight the importance of: accurately modelling the wind speed-to-power output relationships at higher wind speeds; taking account of power curve trends when training models; and the need to incorporate long-term (months to years) power curve variability into the forecast updating process.

KW - Forecast assessment

KW - Short-term forecasting

KW - Wind energy

KW - Wind power forecast

KW - Wind turbine power curve

UR - https://www.scopus.com/pages/publications/85027167138

U2 - 10.1109/EEM.2017.7981885

DO - 10.1109/EEM.2017.7981885

M3 - Conference contribution

AN - SCOPUS:85027167138

T3 - International Conference on the European Energy Market, EEM

BT - 2017 14th International Conference on the European Energy Market, EEM 2017

PB - IEEE Computer Society

T2 - 14th International Conference on the European Energy Market, EEM 2017

Y2 - 6 June 2017 through 9 June 2017

ER -

The impact of power curve estimation on commercial wind power forecasts - An empirical analysis

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Fingerprint

Cite this