A hybrid wind speed forecasting strategy based on Hilbert-Huang transform and machine learning algorithms

Nikita Tomin; Denis Sidorov; Victor Kurbatsky; Vadim Spiryaev; Alexey Zhukov; Paul Leahy

doi:10.1109/POWERCON.2014.6993990

A hybrid wind speed forecasting strategy based on Hilbert-Huang transform and machine learning algorithms

Nikita Tomin
, Denis Sidorov
, Victor Kurbatsky
, Vadim Spiryaev
, Alexey Zhukov
, Paul Leahy

Research output: Chapter in Book/Report/Conference proceedings › Conference proceeding › peer-review

Abstract

Precise wind resource assessment is one of the more imminent challenges. In the present work, we develop an adaptive approach to wind speed forecasting. The approach is based on a combination of the efficient apparatus of non-stationary time series of wind speed retrospective data analysis based on the Hilbert-Huang transform and machine learning models. Models that are examined include neural networks, support vector machines, the regression trees approach: random forest and boosting trees. Evaluation results are presented for the Irish power system based on the Atlantic offshore buoy data.

Original language	English
Title of host publication	POWERCON 2014 - 2014 International Conference on Power System Technology
Subtitle of host publication	Towards Green, Efficient and Smart Power System, Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2980-2986
Number of pages	7
ISBN (Electronic)	9781479950324
DOIs	https://doi.org/10.1109/POWERCON.2014.6993990
Publication status	Published - 18 Dec 2014
Event	2014 International Conference on Power System Technology, POWERCON 2014 - Chengdu, China Duration: 20 Oct 2014 → 22 Oct 2014

Publication series

Name	POWERCON 2014 - 2014 International Conference on Power System Technology: Towards Green, Efficient and Smart Power System, Proceedings

Conference

Conference	2014 International Conference on Power System Technology, POWERCON 2014
Country/Territory	China
City	Chengdu
Period	20/10/14 → 22/10/14

UN SDGs

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

SDG 7 Affordable and Clean Energy

Keywords

forecasting
Hilbert-Huang transform
machine learning
power systems
wind power

Access to Document

10.1109/POWERCON.2014.6993990

Cite this

Tomin, N., Sidorov, D., Kurbatsky, V., Spiryaev, V., Zhukov, A., & Leahy, P. (2014). A hybrid wind speed forecasting strategy based on Hilbert-Huang transform and machine learning algorithms. In POWERCON 2014 - 2014 International Conference on Power System Technology: Towards Green, Efficient and Smart Power System, Proceedings (pp. 2980-2986). Article 6993990 (POWERCON 2014 - 2014 International Conference on Power System Technology: Towards Green, Efficient and Smart Power System, Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/POWERCON.2014.6993990

Tomin, Nikita ; Sidorov, Denis ; Kurbatsky, Victor et al. / A hybrid wind speed forecasting strategy based on Hilbert-Huang transform and machine learning algorithms. POWERCON 2014 - 2014 International Conference on Power System Technology: Towards Green, Efficient and Smart Power System, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 2980-2986 (POWERCON 2014 - 2014 International Conference on Power System Technology: Towards Green, Efficient and Smart Power System, Proceedings).

@inproceedings{5ad7c9c6953c4f7799e4f933db51cdc9,

title = "A hybrid wind speed forecasting strategy based on Hilbert-Huang transform and machine learning algorithms",

abstract = "Precise wind resource assessment is one of the more imminent challenges. In the present work, we develop an adaptive approach to wind speed forecasting. The approach is based on a combination of the efficient apparatus of non-stationary time series of wind speed retrospective data analysis based on the Hilbert-Huang transform and machine learning models. Models that are examined include neural networks, support vector machines, the regression trees approach: random forest and boosting trees. Evaluation results are presented for the Irish power system based on the Atlantic offshore buoy data.",

keywords = "forecasting, Hilbert-Huang transform, machine learning, power systems, wind power",

author = "Nikita Tomin and Denis Sidorov and Victor Kurbatsky and Vadim Spiryaev and Alexey Zhukov and Paul Leahy",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 2014 International Conference on Power System Technology, POWERCON 2014 ; Conference date: 20-10-2014 Through 22-10-2014",

year = "2014",

month = dec,

day = "18",

doi = "10.1109/POWERCON.2014.6993990",

language = "English",

series = "POWERCON 2014 - 2014 International Conference on Power System Technology: Towards Green, Efficient and Smart Power System, Proceedings",

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

pages = "2980--2986",

booktitle = "POWERCON 2014 - 2014 International Conference on Power System Technology",

address = "United States",

}

Tomin, N, Sidorov, D, Kurbatsky, V, Spiryaev, V, Zhukov, A & Leahy, P 2014, A hybrid wind speed forecasting strategy based on Hilbert-Huang transform and machine learning algorithms. in POWERCON 2014 - 2014 International Conference on Power System Technology: Towards Green, Efficient and Smart Power System, Proceedings., 6993990, POWERCON 2014 - 2014 International Conference on Power System Technology: Towards Green, Efficient and Smart Power System, Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 2980-2986, 2014 International Conference on Power System Technology, POWERCON 2014, Chengdu, China, 20/10/14. https://doi.org/10.1109/POWERCON.2014.6993990

A hybrid wind speed forecasting strategy based on Hilbert-Huang transform and machine learning algorithms. / Tomin, Nikita; Sidorov, Denis; Kurbatsky, Victor et al.
POWERCON 2014 - 2014 International Conference on Power System Technology: Towards Green, Efficient and Smart Power System, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2014. p. 2980-2986 6993990 (POWERCON 2014 - 2014 International Conference on Power System Technology: Towards Green, Efficient and Smart Power System, Proceedings).

Research output: Chapter in Book/Report/Conference proceedings › Conference proceeding › peer-review

TY - GEN

T1 - A hybrid wind speed forecasting strategy based on Hilbert-Huang transform and machine learning algorithms

AU - Tomin, Nikita

AU - Sidorov, Denis

AU - Kurbatsky, Victor

AU - Spiryaev, Vadim

AU - Zhukov, Alexey

AU - Leahy, Paul

PY - 2014/12/18

Y1 - 2014/12/18

N2 - Precise wind resource assessment is one of the more imminent challenges. In the present work, we develop an adaptive approach to wind speed forecasting. The approach is based on a combination of the efficient apparatus of non-stationary time series of wind speed retrospective data analysis based on the Hilbert-Huang transform and machine learning models. Models that are examined include neural networks, support vector machines, the regression trees approach: random forest and boosting trees. Evaluation results are presented for the Irish power system based on the Atlantic offshore buoy data.

AB - Precise wind resource assessment is one of the more imminent challenges. In the present work, we develop an adaptive approach to wind speed forecasting. The approach is based on a combination of the efficient apparatus of non-stationary time series of wind speed retrospective data analysis based on the Hilbert-Huang transform and machine learning models. Models that are examined include neural networks, support vector machines, the regression trees approach: random forest and boosting trees. Evaluation results are presented for the Irish power system based on the Atlantic offshore buoy data.

KW - forecasting

KW - Hilbert-Huang transform

KW - machine learning

KW - power systems

KW - wind power

UR - https://www.scopus.com/pages/publications/84924364709

U2 - 10.1109/POWERCON.2014.6993990

DO - 10.1109/POWERCON.2014.6993990

M3 - Conference proceeding

AN - SCOPUS:84924364709

T3 - POWERCON 2014 - 2014 International Conference on Power System Technology: Towards Green, Efficient and Smart Power System, Proceedings

SP - 2980

EP - 2986

BT - POWERCON 2014 - 2014 International Conference on Power System Technology

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2014 International Conference on Power System Technology, POWERCON 2014

Y2 - 20 October 2014 through 22 October 2014

ER -

Tomin N, Sidorov D, Kurbatsky V, Spiryaev V, Zhukov A, Leahy P. A hybrid wind speed forecasting strategy based on Hilbert-Huang transform and machine learning algorithms. In POWERCON 2014 - 2014 International Conference on Power System Technology: Towards Green, Efficient and Smart Power System, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2014. p. 2980-2986. 6993990. (POWERCON 2014 - 2014 International Conference on Power System Technology: Towards Green, Efficient and Smart Power System, Proceedings). doi: 10.1109/POWERCON.2014.6993990

A hybrid wind speed forecasting strategy based on Hilbert-Huang transform and machine learning algorithms

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this