An adaptive time-resolution method for ultra-short-term wind power prediction

Lijuan Li, Yuan Li, Bin Zhou, Qiuwei Wu, Xiaoyang Shen, Hongliang Liu, Zheng Gong

Research output: Contribution to journalJournal articleResearchpeer-review

Abstract

Accurate wind power prediction (WPP) plays an important role in the secure operation and dispatch of power systems. This paper proposes an adaptive time-resolution method to improve the accuracy of ultra-short-term wind power prediction (USTWPP). Firstly, the hidden prediction error (HPE) with its fluctuation magnitude and rate indicators is defined to reveal the fluctuation characteristics of real-time wind power. Then, the adjustment time of time-resolution can be dynamically determined by evaluating the fluctuation magnitudes, and the adjustment rules are formulated by mining the regularities of fluctuation rate of historical wind power data and establishing the interval grouping optimization model. Finally, by coupling the adjustment time and rules into the prediction model of back propagation neural network (BPNN), the rolling prediction with adaptive adjustment of time-resolution is achieved. Extensive tests have not only demonstrated the validity of the proposed method, but also confirmed its capability to cope with the USTWPP especially under situations of extremely violent fluctuations of wind power.
Original languageEnglish
Article number105814
JournalInternational Journal of Electrical Power and Energy Systems
Volume118
Number of pages29
ISSN0142-0615
DOIs
Publication statusPublished - 2020

Keywords

  • Adaptive prediction
  • Neural network
  • Prediction error
  • Prediction model
  • Wind power prediction

Cite this

Li, Lijuan ; Li, Yuan ; Zhou, Bin ; Wu, Qiuwei ; Shen, Xiaoyang ; Liu, Hongliang ; Gong, Zheng. / An adaptive time-resolution method for ultra-short-term wind power prediction. In: International Journal of Electrical Power and Energy Systems. 2020 ; Vol. 118.
@article{bb1ed79a488b44e4b8527f1aea47dfe4,
title = "An adaptive time-resolution method for ultra-short-term wind power prediction",
abstract = "Accurate wind power prediction (WPP) plays an important role in the secure operation and dispatch of power systems. This paper proposes an adaptive time-resolution method to improve the accuracy of ultra-short-term wind power prediction (USTWPP). Firstly, the hidden prediction error (HPE) with its fluctuation magnitude and rate indicators is defined to reveal the fluctuation characteristics of real-time wind power. Then, the adjustment time of time-resolution can be dynamically determined by evaluating the fluctuation magnitudes, and the adjustment rules are formulated by mining the regularities of fluctuation rate of historical wind power data and establishing the interval grouping optimization model. Finally, by coupling the adjustment time and rules into the prediction model of back propagation neural network (BPNN), the rolling prediction with adaptive adjustment of time-resolution is achieved. Extensive tests have not only demonstrated the validity of the proposed method, but also confirmed its capability to cope with the USTWPP especially under situations of extremely violent fluctuations of wind power.",
keywords = "Adaptive prediction, Neural network, Prediction error, Prediction model, Wind power prediction",
author = "Lijuan Li and Yuan Li and Bin Zhou and Qiuwei Wu and Xiaoyang Shen and Hongliang Liu and Zheng Gong",
year = "2020",
doi = "10.1016/j.ijepes.2019.105814",
language = "English",
volume = "118",
journal = "International Journal of Electrical Power & Energy Systems",
issn = "0142-0615",
publisher = "Elsevier",

}

An adaptive time-resolution method for ultra-short-term wind power prediction. / Li, Lijuan; Li, Yuan; Zhou, Bin; Wu, Qiuwei; Shen, Xiaoyang; Liu, Hongliang; Gong, Zheng.

In: International Journal of Electrical Power and Energy Systems, Vol. 118, 105814, 2020.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - An adaptive time-resolution method for ultra-short-term wind power prediction

AU - Li, Lijuan

AU - Li, Yuan

AU - Zhou, Bin

AU - Wu, Qiuwei

AU - Shen, Xiaoyang

AU - Liu, Hongliang

AU - Gong, Zheng

PY - 2020

Y1 - 2020

N2 - Accurate wind power prediction (WPP) plays an important role in the secure operation and dispatch of power systems. This paper proposes an adaptive time-resolution method to improve the accuracy of ultra-short-term wind power prediction (USTWPP). Firstly, the hidden prediction error (HPE) with its fluctuation magnitude and rate indicators is defined to reveal the fluctuation characteristics of real-time wind power. Then, the adjustment time of time-resolution can be dynamically determined by evaluating the fluctuation magnitudes, and the adjustment rules are formulated by mining the regularities of fluctuation rate of historical wind power data and establishing the interval grouping optimization model. Finally, by coupling the adjustment time and rules into the prediction model of back propagation neural network (BPNN), the rolling prediction with adaptive adjustment of time-resolution is achieved. Extensive tests have not only demonstrated the validity of the proposed method, but also confirmed its capability to cope with the USTWPP especially under situations of extremely violent fluctuations of wind power.

AB - Accurate wind power prediction (WPP) plays an important role in the secure operation and dispatch of power systems. This paper proposes an adaptive time-resolution method to improve the accuracy of ultra-short-term wind power prediction (USTWPP). Firstly, the hidden prediction error (HPE) with its fluctuation magnitude and rate indicators is defined to reveal the fluctuation characteristics of real-time wind power. Then, the adjustment time of time-resolution can be dynamically determined by evaluating the fluctuation magnitudes, and the adjustment rules are formulated by mining the regularities of fluctuation rate of historical wind power data and establishing the interval grouping optimization model. Finally, by coupling the adjustment time and rules into the prediction model of back propagation neural network (BPNN), the rolling prediction with adaptive adjustment of time-resolution is achieved. Extensive tests have not only demonstrated the validity of the proposed method, but also confirmed its capability to cope with the USTWPP especially under situations of extremely violent fluctuations of wind power.

KW - Adaptive prediction

KW - Neural network

KW - Prediction error

KW - Prediction model

KW - Wind power prediction

U2 - 10.1016/j.ijepes.2019.105814

DO - 10.1016/j.ijepes.2019.105814

M3 - Journal article

VL - 118

JO - International Journal of Electrical Power & Energy Systems

JF - International Journal of Electrical Power & Energy Systems

SN - 0142-0615

M1 - 105814

ER -