Forecast of Infrequent Wind Power Ramps Based on Data Sampling Strategy

Yuka Takahashi, Yu Fujimoto, Yasuhiro Hayashi

Research output: Contribution to journalConference article

3 Citations (Scopus)

Abstract

The introduction of wind power generation has been promoted in Japan. However, wind power is an unstable power source because its output varies according to the weather. Particularly, sudden changes in output, which could adversely affect the power system, are called ramps and may cause serious problems in the power system. In this paper, the authors discuss the ramp event forecast by using classifiers. A serious issue in this setup is that classification based forecast tends to be inaccurate since the occurrence of such a ramp is relatively rare. This problem is called the class imbalance problem in the machine learning field. To overcome the class imbalance problem in ramp forecast, several data sampling approaches are implemented. The effectiveness of these sampling approaches is experimentally evaluated by using a real-world wind power generation dataset. The results show that the implemented approaches drastically improved the forecast accuracy.

Original languageEnglish
Pages (from-to)496-503
Number of pages8
JournalEnergy Procedia
Volume135
DOIs
Publication statusPublished - 2017 Jan 1
Event11th International Renewable Energy Storage Conference, IRES 2017 - Dusseldorf, Germany
Duration: 2017 Mar 142017 Mar 16

Fingerprint

Wind power
Sampling
Power generation
Learning systems
Classifiers

Keywords

  • class imbalance problem
  • data sampling
  • forecast
  • ramp events
  • wind power

ASJC Scopus subject areas

  • Energy(all)

Cite this

Forecast of Infrequent Wind Power Ramps Based on Data Sampling Strategy. / Takahashi, Yuka; Fujimoto, Yu; Hayashi, Yasuhiro.

In: Energy Procedia, Vol. 135, 01.01.2017, p. 496-503.

Research output: Contribution to journalConference article

@article{1ca92ba01ff54518b338b009f8e5b884,
title = "Forecast of Infrequent Wind Power Ramps Based on Data Sampling Strategy",
abstract = "The introduction of wind power generation has been promoted in Japan. However, wind power is an unstable power source because its output varies according to the weather. Particularly, sudden changes in output, which could adversely affect the power system, are called ramps and may cause serious problems in the power system. In this paper, the authors discuss the ramp event forecast by using classifiers. A serious issue in this setup is that classification based forecast tends to be inaccurate since the occurrence of such a ramp is relatively rare. This problem is called the class imbalance problem in the machine learning field. To overcome the class imbalance problem in ramp forecast, several data sampling approaches are implemented. The effectiveness of these sampling approaches is experimentally evaluated by using a real-world wind power generation dataset. The results show that the implemented approaches drastically improved the forecast accuracy.",
keywords = "class imbalance problem, data sampling, forecast, ramp events, wind power",
author = "Yuka Takahashi and Yu Fujimoto and Yasuhiro Hayashi",
year = "2017",
month = "1",
day = "1",
doi = "10.1016/j.egypro.2017.09.494",
language = "English",
volume = "135",
pages = "496--503",
journal = "Energy Procedia",
issn = "1876-6102",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - Forecast of Infrequent Wind Power Ramps Based on Data Sampling Strategy

AU - Takahashi, Yuka

AU - Fujimoto, Yu

AU - Hayashi, Yasuhiro

PY - 2017/1/1

Y1 - 2017/1/1

N2 - The introduction of wind power generation has been promoted in Japan. However, wind power is an unstable power source because its output varies according to the weather. Particularly, sudden changes in output, which could adversely affect the power system, are called ramps and may cause serious problems in the power system. In this paper, the authors discuss the ramp event forecast by using classifiers. A serious issue in this setup is that classification based forecast tends to be inaccurate since the occurrence of such a ramp is relatively rare. This problem is called the class imbalance problem in the machine learning field. To overcome the class imbalance problem in ramp forecast, several data sampling approaches are implemented. The effectiveness of these sampling approaches is experimentally evaluated by using a real-world wind power generation dataset. The results show that the implemented approaches drastically improved the forecast accuracy.

AB - The introduction of wind power generation has been promoted in Japan. However, wind power is an unstable power source because its output varies according to the weather. Particularly, sudden changes in output, which could adversely affect the power system, are called ramps and may cause serious problems in the power system. In this paper, the authors discuss the ramp event forecast by using classifiers. A serious issue in this setup is that classification based forecast tends to be inaccurate since the occurrence of such a ramp is relatively rare. This problem is called the class imbalance problem in the machine learning field. To overcome the class imbalance problem in ramp forecast, several data sampling approaches are implemented. The effectiveness of these sampling approaches is experimentally evaluated by using a real-world wind power generation dataset. The results show that the implemented approaches drastically improved the forecast accuracy.

KW - class imbalance problem

KW - data sampling

KW - forecast

KW - ramp events

KW - wind power

UR - http://www.scopus.com/inward/record.url?scp=85035113640&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85035113640&partnerID=8YFLogxK

U2 - 10.1016/j.egypro.2017.09.494

DO - 10.1016/j.egypro.2017.09.494

M3 - Conference article

VL - 135

SP - 496

EP - 503

JO - Energy Procedia

JF - Energy Procedia

SN - 1876-6102

ER -