Feature extraction of numerical weather prediction results toward reliable wind power prediction

Kazutoshi Higashiyama, Yu Fujimoto, Yasuhiro Hayashi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Wind power prediction is necessary for stable operation of a power grid under the introduction of significant wind power generation. Wind power prediction approaches based on the results of numerical weather prediction (NWP) have been developed successfully in recent years. However, the high dimensionality of NWP results can be a major obstacle when training models. This paper proposes a feature extraction scheme based on convolutional neural networks to compress high-dimensional NWP results by deriving critically important low-dimensional information for wind power prediction. The experimental results show that the proposed feature extractor can contribute to the improvement of wind power prediction accuracy.

Original languageEnglish
Title of host publication2017 IEEE PES Innovative Smart Grid Technologies Conference Europe, ISGT-Europe 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-6
Number of pages6
Volume2018-January
ISBN (Electronic)9781538619537
DOIs
Publication statusPublished - 2018 Jan 16
Event2017 IEEE PES Innovative Smart Grid Technologies Conference Europe, ISGT-Europe 2017 - Torino, Italy
Duration: 2017 Sep 262017 Sep 29

Other

Other2017 IEEE PES Innovative Smart Grid Technologies Conference Europe, ISGT-Europe 2017
CountryItaly
CityTorino
Period17/9/2617/9/29

Fingerprint

Wind power
Feature extraction
Power generation
Neural networks

Keywords

  • Convolutional neural network
  • deep learning
  • feature extraction
  • numerical weather prediction
  • wind power prediction

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Electrical and Electronic Engineering
  • Energy Engineering and Power Technology

Cite this

Higashiyama, K., Fujimoto, Y., & Hayashi, Y. (2018). Feature extraction of numerical weather prediction results toward reliable wind power prediction. In 2017 IEEE PES Innovative Smart Grid Technologies Conference Europe, ISGT-Europe 2017 - Proceedings (Vol. 2018-January, pp. 1-6). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISGTEurope.2017.8260216

Feature extraction of numerical weather prediction results toward reliable wind power prediction. / Higashiyama, Kazutoshi; Fujimoto, Yu; Hayashi, Yasuhiro.

2017 IEEE PES Innovative Smart Grid Technologies Conference Europe, ISGT-Europe 2017 - Proceedings. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. p. 1-6.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Higashiyama, K, Fujimoto, Y & Hayashi, Y 2018, Feature extraction of numerical weather prediction results toward reliable wind power prediction. in 2017 IEEE PES Innovative Smart Grid Technologies Conference Europe, ISGT-Europe 2017 - Proceedings. vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 1-6, 2017 IEEE PES Innovative Smart Grid Technologies Conference Europe, ISGT-Europe 2017, Torino, Italy, 17/9/26. https://doi.org/10.1109/ISGTEurope.2017.8260216
Higashiyama K, Fujimoto Y, Hayashi Y. Feature extraction of numerical weather prediction results toward reliable wind power prediction. In 2017 IEEE PES Innovative Smart Grid Technologies Conference Europe, ISGT-Europe 2017 - Proceedings. Vol. 2018-January. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1-6 https://doi.org/10.1109/ISGTEurope.2017.8260216
Higashiyama, Kazutoshi ; Fujimoto, Yu ; Hayashi, Yasuhiro. / Feature extraction of numerical weather prediction results toward reliable wind power prediction. 2017 IEEE PES Innovative Smart Grid Technologies Conference Europe, ISGT-Europe 2017 - Proceedings. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1-6
@inproceedings{07a495a26ac141d191bcdb976ade4d51,
title = "Feature extraction of numerical weather prediction results toward reliable wind power prediction",
abstract = "Wind power prediction is necessary for stable operation of a power grid under the introduction of significant wind power generation. Wind power prediction approaches based on the results of numerical weather prediction (NWP) have been developed successfully in recent years. However, the high dimensionality of NWP results can be a major obstacle when training models. This paper proposes a feature extraction scheme based on convolutional neural networks to compress high-dimensional NWP results by deriving critically important low-dimensional information for wind power prediction. The experimental results show that the proposed feature extractor can contribute to the improvement of wind power prediction accuracy.",
keywords = "Convolutional neural network, deep learning, feature extraction, numerical weather prediction, wind power prediction",
author = "Kazutoshi Higashiyama and Yu Fujimoto and Yasuhiro Hayashi",
year = "2018",
month = "1",
day = "16",
doi = "10.1109/ISGTEurope.2017.8260216",
language = "English",
volume = "2018-January",
pages = "1--6",
booktitle = "2017 IEEE PES Innovative Smart Grid Technologies Conference Europe, ISGT-Europe 2017 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Feature extraction of numerical weather prediction results toward reliable wind power prediction

AU - Higashiyama, Kazutoshi

AU - Fujimoto, Yu

AU - Hayashi, Yasuhiro

PY - 2018/1/16

Y1 - 2018/1/16

N2 - Wind power prediction is necessary for stable operation of a power grid under the introduction of significant wind power generation. Wind power prediction approaches based on the results of numerical weather prediction (NWP) have been developed successfully in recent years. However, the high dimensionality of NWP results can be a major obstacle when training models. This paper proposes a feature extraction scheme based on convolutional neural networks to compress high-dimensional NWP results by deriving critically important low-dimensional information for wind power prediction. The experimental results show that the proposed feature extractor can contribute to the improvement of wind power prediction accuracy.

AB - Wind power prediction is necessary for stable operation of a power grid under the introduction of significant wind power generation. Wind power prediction approaches based on the results of numerical weather prediction (NWP) have been developed successfully in recent years. However, the high dimensionality of NWP results can be a major obstacle when training models. This paper proposes a feature extraction scheme based on convolutional neural networks to compress high-dimensional NWP results by deriving critically important low-dimensional information for wind power prediction. The experimental results show that the proposed feature extractor can contribute to the improvement of wind power prediction accuracy.

KW - Convolutional neural network

KW - deep learning

KW - feature extraction

KW - numerical weather prediction

KW - wind power prediction

UR - http://www.scopus.com/inward/record.url?scp=85046288429&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046288429&partnerID=8YFLogxK

U2 - 10.1109/ISGTEurope.2017.8260216

DO - 10.1109/ISGTEurope.2017.8260216

M3 - Conference contribution

VL - 2018-January

SP - 1

EP - 6

BT - 2017 IEEE PES Innovative Smart Grid Technologies Conference Europe, ISGT-Europe 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -