An Advanced Approach for Construction of Optimal Wind Power Prediction Intervals

Guoyong Zhang; Yonggang Wu; Kit Po Wong; Zhao Xu; Zhao Yang Dong; Herbert Ho-Ching Iu

doi:10.1109/TPWRS.2014.2363873

An Advanced Approach for Construction of Optimal Wind Power Prediction Intervals

Guoyong Zhang
, Yonggang Wu
, Kit Po Wong
, Zhao Xu
, Zhao Yang Dong
, Herbert Ho-Ching Iu

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

95 Citations (Scopus)

Abstract

High-quality wind power prediction intervals (PIs) are of utmost importance for system planning and operation. To improve the reliability and sharpness of PIs, this paper proposes a new approach in which the original wind power series is first decomposed and grouped into components of reduced order of complexity using ensemble empirical mode decomposition and sample entropy techniques. The methods for the prediction of these components with extreme learning machine technique and the formation of the overall optimal PIs are then described. The effectiveness of proposed approach is demonstrated by applying it to real wind farms from Australia and National Renewable Energy Laboratory. Compared to the existing methods without wind power series decomposition, the proposed approach is found to be more effective for wind power interval forecasts with higher reliability and sharpness. © 1969-2012 IEEE.

Original language	English
Article number	6936937
Pages (from-to)	2706-2715
Journal	IEEE Transactions on Power Systems
Volume	30
Issue number	5
DOIs	https://doi.org/10.1109/TPWRS.2014.2363873
Publication status	Published - 1 Sept 2015
Externally published	Yes

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Research Keywords

Ensemble empirical mode decomposition
extreme learning machine
prediction intervals
sample entropy
wind power

Access Output

10.1109/TPWRS.2014.2363873

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{67f5cff3609b44d2aa7a38ca518c1c58,

title = "An Advanced Approach for Construction of Optimal Wind Power Prediction Intervals",

abstract = "High-quality wind power prediction intervals (PIs) are of utmost importance for system planning and operation. To improve the reliability and sharpness of PIs, this paper proposes a new approach in which the original wind power series is first decomposed and grouped into components of reduced order of complexity using ensemble empirical mode decomposition and sample entropy techniques. The methods for the prediction of these components with extreme learning machine technique and the formation of the overall optimal PIs are then described. The effectiveness of proposed approach is demonstrated by applying it to real wind farms from Australia and National Renewable Energy Laboratory. Compared to the existing methods without wind power series decomposition, the proposed approach is found to be more effective for wind power interval forecasts with higher reliability and sharpness. {\textcopyright} 1969-2012 IEEE.",

keywords = "Ensemble empirical mode decomposition, extreme learning machine, prediction intervals, sample entropy, wind power",

author = "Guoyong Zhang and Yonggang Wu and Wong, \{Kit Po\} and Zhao Xu and Dong, \{Zhao Yang\} and Iu, \{Herbert Ho-Ching\}",

note = "Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].",

year = "2015",

month = sep,

day = "1",

doi = "10.1109/TPWRS.2014.2363873",

language = "English",

volume = "30",

pages = "2706--2715",

journal = "IEEE Transactions on Power Systems",

issn = "0885-8950",

publisher = "IEEE",

number = "5",

}

TY - JOUR

T1 - An Advanced Approach for Construction of Optimal Wind Power Prediction Intervals

AU - Zhang, Guoyong

AU - Wu, Yonggang

AU - Wong, Kit Po

AU - Xu, Zhao

AU - Dong, Zhao Yang

AU - Iu, Herbert Ho-Ching

N1 - Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

PY - 2015/9/1

Y1 - 2015/9/1

N2 - High-quality wind power prediction intervals (PIs) are of utmost importance for system planning and operation. To improve the reliability and sharpness of PIs, this paper proposes a new approach in which the original wind power series is first decomposed and grouped into components of reduced order of complexity using ensemble empirical mode decomposition and sample entropy techniques. The methods for the prediction of these components with extreme learning machine technique and the formation of the overall optimal PIs are then described. The effectiveness of proposed approach is demonstrated by applying it to real wind farms from Australia and National Renewable Energy Laboratory. Compared to the existing methods without wind power series decomposition, the proposed approach is found to be more effective for wind power interval forecasts with higher reliability and sharpness. © 1969-2012 IEEE.

AB - High-quality wind power prediction intervals (PIs) are of utmost importance for system planning and operation. To improve the reliability and sharpness of PIs, this paper proposes a new approach in which the original wind power series is first decomposed and grouped into components of reduced order of complexity using ensemble empirical mode decomposition and sample entropy techniques. The methods for the prediction of these components with extreme learning machine technique and the formation of the overall optimal PIs are then described. The effectiveness of proposed approach is demonstrated by applying it to real wind farms from Australia and National Renewable Energy Laboratory. Compared to the existing methods without wind power series decomposition, the proposed approach is found to be more effective for wind power interval forecasts with higher reliability and sharpness. © 1969-2012 IEEE.

KW - Ensemble empirical mode decomposition

KW - extreme learning machine

KW - prediction intervals

KW - sample entropy

KW - wind power

UR - https://www.scopus.com/pages/publications/85027943440

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85027943440&origin=recordpage

U2 - 10.1109/TPWRS.2014.2363873

DO - 10.1109/TPWRS.2014.2363873

M3 - RGC 21 - Publication in refereed journal

SN - 0885-8950

VL - 30

SP - 2706

EP - 2715

JO - IEEE Transactions on Power Systems

JF - IEEE Transactions on Power Systems

IS - 5

M1 - 6936937

ER -

An Advanced Approach for Construction of Optimal Wind Power Prediction Intervals

Abstract

Bibliographical note

UN SDGs

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this