Method selection in different regions for short-term wind speed prediction in Japan

Ikki Tanaka; Hiromitsu Ohmori

doi:10.1109/SICE.2015.7285424

Method selection in different regions for short-term wind speed prediction in Japan

Ikki Tanaka, Hiromitsu Ohmori

Department of System Design Engineering

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

11 Citations (Scopus)

Abstract

Recently, many approaches have been proposed in wind speed prediction. However they are verified only in certain areas, and have not been a quantitative verification in many different locations. Therefore, this paper used the data of the various parts of Japan for the one-step-ahead prediction, and applied a number of different approaches to each point. And then it was evaluated such as MAE. These models are persistent model, ARMA-GARCH model, non-linear autoregressive network with an external input (NARX), recurrent neural network (RNN), and support vector regression (SVR). From the results of the numerical simulation at each point, this paper presents the results that it is difficult to create the same model which minimize the error in all areas, and there is a need to create a predictor for each region.

Original language	English
Title of host publication	2015 54th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	189-194
Number of pages	6
ISBN (Print)	9784907764487
DOIs	https://doi.org/10.1109/SICE.2015.7285424
Publication status	Published - 2015 Sept 30
Event	54th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2015 - Hangzhou, China Duration: 2015 Jul 28 → 2015 Jul 30

Other

Other	54th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2015
Country/Territory	China
City	Hangzhou
Period	15/7/28 → 15/7/30

Keywords

ARMA
GARCH
non-linear autoregressive network with an external input (NARX)
prediction model
recurrent neural network (RNN)
support vector regression (SVR)
Wind speed

ASJC Scopus subject areas

Control and Systems Engineering

Access to Document

10.1109/SICE.2015.7285424

Cite this

Method selection in different regions for short-term wind speed prediction in Japan. / Tanaka, Ikki; Ohmori, Hiromitsu.
2015 54th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 189-194 7285424.

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

Tanaka, I & Ohmori, H 2015, Method selection in different regions for short-term wind speed prediction in Japan. in 2015 54th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2015., 7285424, Institute of Electrical and Electronics Engineers Inc., pp. 189-194, 54th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2015, Hangzhou, China, 15/7/28. https://doi.org/10.1109/SICE.2015.7285424

@inproceedings{49b5f35404c64f1fa97641ff816fcaf0,

title = "Method selection in different regions for short-term wind speed prediction in Japan",

abstract = "Recently, many approaches have been proposed in wind speed prediction. However they are verified only in certain areas, and have not been a quantitative verification in many different locations. Therefore, this paper used the data of the various parts of Japan for the one-step-ahead prediction, and applied a number of different approaches to each point. And then it was evaluated such as MAE. These models are persistent model, ARMA-GARCH model, non-linear autoregressive network with an external input (NARX), recurrent neural network (RNN), and support vector regression (SVR). From the results of the numerical simulation at each point, this paper presents the results that it is difficult to create the same model which minimize the error in all areas, and there is a need to create a predictor for each region.",

keywords = "ARMA, GARCH, non-linear autoregressive network with an external input (NARX), prediction model, recurrent neural network (RNN), support vector regression (SVR), Wind speed",

author = "Ikki Tanaka and Hiromitsu Ohmori",

year = "2015",

month = sep,

day = "30",

doi = "10.1109/SICE.2015.7285424",

language = "English",

isbn = "9784907764487",

pages = "189--194",

booktitle = "2015 54th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2015",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "54th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2015 ; Conference date: 28-07-2015 Through 30-07-2015",

}

TY - GEN

T1 - Method selection in different regions for short-term wind speed prediction in Japan

AU - Tanaka, Ikki

AU - Ohmori, Hiromitsu

PY - 2015/9/30

Y1 - 2015/9/30

N2 - Recently, many approaches have been proposed in wind speed prediction. However they are verified only in certain areas, and have not been a quantitative verification in many different locations. Therefore, this paper used the data of the various parts of Japan for the one-step-ahead prediction, and applied a number of different approaches to each point. And then it was evaluated such as MAE. These models are persistent model, ARMA-GARCH model, non-linear autoregressive network with an external input (NARX), recurrent neural network (RNN), and support vector regression (SVR). From the results of the numerical simulation at each point, this paper presents the results that it is difficult to create the same model which minimize the error in all areas, and there is a need to create a predictor for each region.

AB - Recently, many approaches have been proposed in wind speed prediction. However they are verified only in certain areas, and have not been a quantitative verification in many different locations. Therefore, this paper used the data of the various parts of Japan for the one-step-ahead prediction, and applied a number of different approaches to each point. And then it was evaluated such as MAE. These models are persistent model, ARMA-GARCH model, non-linear autoregressive network with an external input (NARX), recurrent neural network (RNN), and support vector regression (SVR). From the results of the numerical simulation at each point, this paper presents the results that it is difficult to create the same model which minimize the error in all areas, and there is a need to create a predictor for each region.

KW - ARMA

KW - GARCH

KW - non-linear autoregressive network with an external input (NARX)

KW - prediction model

KW - recurrent neural network (RNN)

KW - support vector regression (SVR)

KW - Wind speed

UR - http://www.scopus.com/inward/record.url?scp=84960119083&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84960119083&partnerID=8YFLogxK

U2 - 10.1109/SICE.2015.7285424

DO - 10.1109/SICE.2015.7285424

M3 - Conference contribution

AN - SCOPUS:84960119083

SN - 9784907764487

SP - 189

EP - 194

BT - 2015 54th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 54th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2015

Y2 - 28 July 2015 through 30 July 2015

ER -

Method selection in different regions for short-term wind speed prediction in Japan

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this