Alerting to Rare Large-Scale Ramp Events in Wind Power Generation

Yu Fujimoto, Yuka Takahashi, Yasuhiro Hayashi

Research output: Contribution to journalArticle

Abstract

Wind power is an unstable power source, as its output fluctuates drastically according to the weather. Such instability can cause sudden large-scale changes in output, called ramp events; the frequency of such events is relatively low throughout the year but they could negatively affect the supply-demand balance in a power system. This study focuses on an alerting scheme of wind power ramp events for a transmission system operator to support operational decisions on cold reserve power plants. The ramp alerting scheme is implemented from the viewpoint of supervised learning by using the prediction results of wind power output. In particular, the authors address the class imbalance problem, as the accuracy of ramp event prediction tends to be low because of the infrequency of such ramp events in the database used for learning. In this study, several data sampling strategies are proposed and implemented to overcome the problem in the ramp alert task. The effectiveness of the proposed data sampling framework is evaluated experimentally by predicting real-world wind power ramps, based on a dataset collected in Japan. The experimental results show that the proposed framework effectively improves the ramp alert accuracy by addressing the class imbalance problem.

LanguageEnglish
Article number8331103
Pages55-65
Number of pages11
JournalIEEE Transactions on Sustainable Energy
Volume10
Issue number1
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

Wind power
Power generation
Sampling
Supervised learning
Power plants

Keywords

  • Class imbalance problem
  • machine learning
  • prediction
  • wind power ramp

ASJC Scopus subject areas

  • Renewable Energy, Sustainability and the Environment

Cite this

Alerting to Rare Large-Scale Ramp Events in Wind Power Generation. / Fujimoto, Yu; Takahashi, Yuka; Hayashi, Yasuhiro.

In: IEEE Transactions on Sustainable Energy, Vol. 10, No. 1, 8331103, 01.01.2019, p. 55-65.

Research output: Contribution to journalArticle

@article{d5ba88bc57a4489795cf4b9d45212952,
title = "Alerting to Rare Large-Scale Ramp Events in Wind Power Generation",
abstract = "Wind power is an unstable power source, as its output fluctuates drastically according to the weather. Such instability can cause sudden large-scale changes in output, called ramp events; the frequency of such events is relatively low throughout the year but they could negatively affect the supply-demand balance in a power system. This study focuses on an alerting scheme of wind power ramp events for a transmission system operator to support operational decisions on cold reserve power plants. The ramp alerting scheme is implemented from the viewpoint of supervised learning by using the prediction results of wind power output. In particular, the authors address the class imbalance problem, as the accuracy of ramp event prediction tends to be low because of the infrequency of such ramp events in the database used for learning. In this study, several data sampling strategies are proposed and implemented to overcome the problem in the ramp alert task. The effectiveness of the proposed data sampling framework is evaluated experimentally by predicting real-world wind power ramps, based on a dataset collected in Japan. The experimental results show that the proposed framework effectively improves the ramp alert accuracy by addressing the class imbalance problem.",
keywords = "Class imbalance problem, machine learning, prediction, wind power ramp",
author = "Yu Fujimoto and Yuka Takahashi and Yasuhiro Hayashi",
year = "2019",
month = "1",
day = "1",
doi = "10.1109/TSTE.2018.2822807",
language = "English",
volume = "10",
pages = "55--65",
journal = "IEEE Transactions on Sustainable Energy",
issn = "1949-3029",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "1",

}

TY - JOUR

T1 - Alerting to Rare Large-Scale Ramp Events in Wind Power Generation

AU - Fujimoto, Yu

AU - Takahashi, Yuka

AU - Hayashi, Yasuhiro

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Wind power is an unstable power source, as its output fluctuates drastically according to the weather. Such instability can cause sudden large-scale changes in output, called ramp events; the frequency of such events is relatively low throughout the year but they could negatively affect the supply-demand balance in a power system. This study focuses on an alerting scheme of wind power ramp events for a transmission system operator to support operational decisions on cold reserve power plants. The ramp alerting scheme is implemented from the viewpoint of supervised learning by using the prediction results of wind power output. In particular, the authors address the class imbalance problem, as the accuracy of ramp event prediction tends to be low because of the infrequency of such ramp events in the database used for learning. In this study, several data sampling strategies are proposed and implemented to overcome the problem in the ramp alert task. The effectiveness of the proposed data sampling framework is evaluated experimentally by predicting real-world wind power ramps, based on a dataset collected in Japan. The experimental results show that the proposed framework effectively improves the ramp alert accuracy by addressing the class imbalance problem.

AB - Wind power is an unstable power source, as its output fluctuates drastically according to the weather. Such instability can cause sudden large-scale changes in output, called ramp events; the frequency of such events is relatively low throughout the year but they could negatively affect the supply-demand balance in a power system. This study focuses on an alerting scheme of wind power ramp events for a transmission system operator to support operational decisions on cold reserve power plants. The ramp alerting scheme is implemented from the viewpoint of supervised learning by using the prediction results of wind power output. In particular, the authors address the class imbalance problem, as the accuracy of ramp event prediction tends to be low because of the infrequency of such ramp events in the database used for learning. In this study, several data sampling strategies are proposed and implemented to overcome the problem in the ramp alert task. The effectiveness of the proposed data sampling framework is evaluated experimentally by predicting real-world wind power ramps, based on a dataset collected in Japan. The experimental results show that the proposed framework effectively improves the ramp alert accuracy by addressing the class imbalance problem.

KW - Class imbalance problem

KW - machine learning

KW - prediction

KW - wind power ramp

UR - http://www.scopus.com/inward/record.url?scp=85059068222&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059068222&partnerID=8YFLogxK

U2 - 10.1109/TSTE.2018.2822807

DO - 10.1109/TSTE.2018.2822807

M3 - Article

VL - 10

SP - 55

EP - 65

JO - IEEE Transactions on Sustainable Energy

T2 - IEEE Transactions on Sustainable Energy

JF - IEEE Transactions on Sustainable Energy

SN - 1949-3029

IS - 1

M1 - 8331103

ER -