Short-term wind power prediction for wind turbine via kalman filter based on JIT modeling

Tomoki Ishikawa, Takaaki Kojima, Toru Namerikawa

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This paper addresses wind power prediction which is known to be a key technology in EMS(Energy Management Systems). In this paper, 24 hours ahead power prediction method using a filtering theory is proposed for wind power generation. The prediction method is a simple algorithm, the procedure of prediction consists of two steps, the data processing and the calculation of predicted values. In the data processing, in order to get the correlative data from the database, we employ JIT(Just-In-Time) Modeling. In the calculation of predicted value, we propose the regression model for wind speed and wind power, and the unknown parameters are estimated via constrained kalman filter. Moreover, in a procedure of estimation of the unknown parameters, reduction and the convergence of them are also guaranteed. Finally, the advantages of the proposed method over the conventional method are shown through actual prediction evaluations.

Original languageEnglish
Pages (from-to)81-89
Number of pages9
JournalIEEJ Transactions on Electronics, Information and Systems
Volume135
Issue number1
DOIs
Publication statusPublished - 2015

Fingerprint

Kalman filters
Wind turbines
Wind power
Energy management systems
Power generation

Keywords

  • Constrained kalman filter
  • Energy management systems (EMS)
  • JIT modeling
  • Short-term prediction
  • Wind power

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Short-term wind power prediction for wind turbine via kalman filter based on JIT modeling. / Ishikawa, Tomoki; Kojima, Takaaki; Namerikawa, Toru.

In: IEEJ Transactions on Electronics, Information and Systems, Vol. 135, No. 1, 2015, p. 81-89.

Research output: Contribution to journalArticle

@article{f9443b5f6d4d44b0827799b676d17715,
title = "Short-term wind power prediction for wind turbine via kalman filter based on JIT modeling",
abstract = "This paper addresses wind power prediction which is known to be a key technology in EMS(Energy Management Systems). In this paper, 24 hours ahead power prediction method using a filtering theory is proposed for wind power generation. The prediction method is a simple algorithm, the procedure of prediction consists of two steps, the data processing and the calculation of predicted values. In the data processing, in order to get the correlative data from the database, we employ JIT(Just-In-Time) Modeling. In the calculation of predicted value, we propose the regression model for wind speed and wind power, and the unknown parameters are estimated via constrained kalman filter. Moreover, in a procedure of estimation of the unknown parameters, reduction and the convergence of them are also guaranteed. Finally, the advantages of the proposed method over the conventional method are shown through actual prediction evaluations.",
keywords = "Constrained kalman filter, Energy management systems (EMS), JIT modeling, Short-term prediction, Wind power",
author = "Tomoki Ishikawa and Takaaki Kojima and Toru Namerikawa",
year = "2015",
doi = "10.1541/ieejeiss.135.81",
language = "English",
volume = "135",
pages = "81--89",
journal = "IEEJ Transactions on Electronics, Information and Systems",
issn = "0385-4221",
publisher = "The Institute of Electrical Engineers of Japan",
number = "1",

}

TY - JOUR

T1 - Short-term wind power prediction for wind turbine via kalman filter based on JIT modeling

AU - Ishikawa, Tomoki

AU - Kojima, Takaaki

AU - Namerikawa, Toru

PY - 2015

Y1 - 2015

N2 - This paper addresses wind power prediction which is known to be a key technology in EMS(Energy Management Systems). In this paper, 24 hours ahead power prediction method using a filtering theory is proposed for wind power generation. The prediction method is a simple algorithm, the procedure of prediction consists of two steps, the data processing and the calculation of predicted values. In the data processing, in order to get the correlative data from the database, we employ JIT(Just-In-Time) Modeling. In the calculation of predicted value, we propose the regression model for wind speed and wind power, and the unknown parameters are estimated via constrained kalman filter. Moreover, in a procedure of estimation of the unknown parameters, reduction and the convergence of them are also guaranteed. Finally, the advantages of the proposed method over the conventional method are shown through actual prediction evaluations.

AB - This paper addresses wind power prediction which is known to be a key technology in EMS(Energy Management Systems). In this paper, 24 hours ahead power prediction method using a filtering theory is proposed for wind power generation. The prediction method is a simple algorithm, the procedure of prediction consists of two steps, the data processing and the calculation of predicted values. In the data processing, in order to get the correlative data from the database, we employ JIT(Just-In-Time) Modeling. In the calculation of predicted value, we propose the regression model for wind speed and wind power, and the unknown parameters are estimated via constrained kalman filter. Moreover, in a procedure of estimation of the unknown parameters, reduction and the convergence of them are also guaranteed. Finally, the advantages of the proposed method over the conventional method are shown through actual prediction evaluations.

KW - Constrained kalman filter

KW - Energy management systems (EMS)

KW - JIT modeling

KW - Short-term prediction

KW - Wind power

UR - http://www.scopus.com/inward/record.url?scp=84920381789&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84920381789&partnerID=8YFLogxK

U2 - 10.1541/ieejeiss.135.81

DO - 10.1541/ieejeiss.135.81

M3 - Article

AN - SCOPUS:84920381789

VL - 135

SP - 81

EP - 89

JO - IEEJ Transactions on Electronics, Information and Systems

JF - IEEJ Transactions on Electronics, Information and Systems

SN - 0385-4221

IS - 1

ER -