Adaptive ultra-short-term wind power prediction based on risk assessment

Yusheng Xue; Chen  Yu; Kang Li; Fushuan Wen; Yi Ding; Qiuwei Wu; Guangya Yang

doi:10.17775/CSEEJPES.2016.00036

Adaptive ultra-short-term wind power prediction based on risk assessment

Yusheng Xue, Chen Yu, Kang Li, Fushuan Wen, Yi Ding, Qiuwei Wu, Guangya Yang

Research output: Contribution to journal › Journal article › Research › peer-review

257 Downloads (Pure)

Abstract

A risk assessment based adaptive ultra-short-term wind power prediction (USTWPP) method is proposed in this paper. The method first extracts features from the historical data, and split every wind power time series (WPTS) into several subsets defined by their stationary patterns. A WPTS that does not match with any of the stationary patterns is then included into a subset of non-stationary patterns. Every WPTS subset is then related to a USTWPP model which is specially selected and optimized offline based on the proposed risk assessment index. For on-line applications, the pattern of the last short WPTS is first recognized, and the relevant prediction model is applied for USTWPP. Experimental results confirm the efficacy of the proposed method.

Original language	English
Journal	CSEE Journal of Power and Energy Systems
Volume	2
Issue number	3
Pages (from-to)	59-64
Number of pages	6
ISSN	2096-0042
DOIs	https://doi.org/10.17775/CSEEJPES.2016.00036
Publication status	Published - 2016

Keywords

Wind power prediction
Time series features
Offline optimization
Online matching
Positive error vs negative error
Error evaluation
Risk index

Access to Document

10.17775/CSEEJPES.2016.00036

07562825Final published version, 298 KB

Fingerprint Dive into the research topics of 'Adaptive ultra-short-term wind power prediction based on risk assessment'. Together they form a unique fingerprint.

Cite this

@article{fb51b9191b5e422c89c2868645af16a0,

title = "Adaptive ultra-short-term wind power prediction based on risk assessment",

abstract = "A risk assessment based adaptive ultra-short-term wind power prediction (USTWPP) method is proposed in this paper. The method first extracts features from the historical data, and split every wind power time series (WPTS) into several subsets defined by their stationary patterns. A WPTS that does not match with any of the stationary patterns is then included into a subset of non-stationary patterns. Every WPTS subset is then related to a USTWPP model which is specially selected and optimized offline based on the proposed risk assessment index. For on-line applications, the pattern of the last short WPTS is first recognized, and the relevant prediction model is applied for USTWPP. Experimental results confirm the efficacy of the proposed method.",

keywords = "Wind power prediction, Time series features, Offline optimization, Online matching, Positive error vs negative error, Error evaluation, Risk index",

author = "Yusheng Xue and Chen Yu and Kang Li and Fushuan Wen and Yi Ding and Qiuwei Wu and Guangya Yang",

year = "2016",

doi = "10.17775/CSEEJPES.2016.00036",

language = "English",

volume = "2",

pages = "59--64",

journal = "CSEE Journal of Power and Energy Systems",

issn = "2096-0042",

publisher = "The Chinese Society for Electrical Engineering (CSEE)",

number = "3",

}

TY - JOUR

T1 - Adaptive ultra-short-term wind power prediction based on risk assessment

AU - Xue, Yusheng

AU - Yu, Chen

AU - Li, Kang

AU - Wen, Fushuan

AU - Ding, Yi

AU - Wu, Qiuwei

AU - Yang, Guangya

PY - 2016

Y1 - 2016

N2 - A risk assessment based adaptive ultra-short-term wind power prediction (USTWPP) method is proposed in this paper. The method first extracts features from the historical data, and split every wind power time series (WPTS) into several subsets defined by their stationary patterns. A WPTS that does not match with any of the stationary patterns is then included into a subset of non-stationary patterns. Every WPTS subset is then related to a USTWPP model which is specially selected and optimized offline based on the proposed risk assessment index. For on-line applications, the pattern of the last short WPTS is first recognized, and the relevant prediction model is applied for USTWPP. Experimental results confirm the efficacy of the proposed method.

AB - A risk assessment based adaptive ultra-short-term wind power prediction (USTWPP) method is proposed in this paper. The method first extracts features from the historical data, and split every wind power time series (WPTS) into several subsets defined by their stationary patterns. A WPTS that does not match with any of the stationary patterns is then included into a subset of non-stationary patterns. Every WPTS subset is then related to a USTWPP model which is specially selected and optimized offline based on the proposed risk assessment index. For on-line applications, the pattern of the last short WPTS is first recognized, and the relevant prediction model is applied for USTWPP. Experimental results confirm the efficacy of the proposed method.

KW - Wind power prediction

KW - Time series features

KW - Offline optimization

KW - Online matching

KW - Positive error vs negative error

KW - Error evaluation

KW - Risk index

U2 - 10.17775/CSEEJPES.2016.00036

DO - 10.17775/CSEEJPES.2016.00036

M3 - Journal article

VL - 2

SP - 59

EP - 64

JO - CSEE Journal of Power and Energy Systems

JF - CSEE Journal of Power and Energy Systems

SN - 2096-0042

IS - 3

ER -