Wind Speed Forecasting Using ARMA and Neural Network Models

Uzair Zaman; Hamid Teimourzadeh; Elias Hassani Sangani; Xiaodong Liang; Chi Yung Chung

doi:10.1109/EPEC52095.2021.9621650

Wind Speed Forecasting Using ARMA and Neural Network Models

Uzair Zaman
, Hamid Teimourzadeh
, Elias Hassani Sangani
, Xiaodong Liang
, Chi Yung Chung

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

20 Citations (Scopus)

Abstract

With the advancement of wind power generation technology, wind power plays an increasing role in modern power grids. To properly consider wind power for power systems planning and operation purpose, wind power and wind speed must be forecasted accurately. Wind is chaotic, random, irregular, and non-stationary in nature, which creates significant challenges in wind speed forecasting. This paper aims to forecast wind speed using both the statistical time series analysis method (autoregressive moving average (ARMA)) and neural network methods (feedforward neural network (FNN), recurrent neural network (RNN), long short-term memory (LSTM), and the gated recurrent unit (GRU)). The performance of the proposed five models is compared with the measured wind speed data, and the GRU model shows the best performance with the highest prediction accuracy. The four ANN models outperform the ARMA model.

Original language	English
Title of host publication	2021 IEEE Electrical Power and Energy Conference, EPEC 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	243-248
Number of pages	6
ISBN (Electronic)	9781665429283
DOIs	https://doi.org/10.1109/EPEC52095.2021.9621650
Publication status	Published - Nov 2021
Externally published	Yes
Event	2021 IEEE Electrical Power and Energy Conference, EPEC 2021 - Virtual, Online, Canada Duration: 22 Oct 2021 → 31 Oct 2021

Publication series

Name	2021 IEEE Electrical Power and Energy Conference, EPEC 2021

Conference

Conference	2021 IEEE Electrical Power and Energy Conference, EPEC 2021
Country/Territory	Canada
City	Virtual, Online
Period	22/10/21 → 31/10/21

UN SDGs

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

SDG 7 Affordable and Clean Energy

Keywords

Artificial Neural Network
autoregressive moving average
gated recurrent unit
wind speed foresting

ASJC Scopus subject areas

Energy Engineering and Power Technology
Renewable Energy, Sustainability and the Environment
Automotive Engineering
Electrical and Electronic Engineering

More information

10.1109/EPEC52095.2021.9621650

Cite this

Zaman, U., Teimourzadeh, H., Sangani, E. H., Liang, X., & Chung, C. Y. (2021). Wind Speed Forecasting Using ARMA and Neural Network Models. In 2021 IEEE Electrical Power and Energy Conference, EPEC 2021 (pp. 243-248). (2021 IEEE Electrical Power and Energy Conference, EPEC 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EPEC52095.2021.9621650

@inproceedings{6b7fcf2b71534c638c8915462f2b5eb4,

title = "Wind Speed Forecasting Using ARMA and Neural Network Models",

abstract = "With the advancement of wind power generation technology, wind power plays an increasing role in modern power grids. To properly consider wind power for power systems planning and operation purpose, wind power and wind speed must be forecasted accurately. Wind is chaotic, random, irregular, and non-stationary in nature, which creates significant challenges in wind speed forecasting. This paper aims to forecast wind speed using both the statistical time series analysis method (autoregressive moving average (ARMA)) and neural network methods (feedforward neural network (FNN), recurrent neural network (RNN), long short-term memory (LSTM), and the gated recurrent unit (GRU)). The performance of the proposed five models is compared with the measured wind speed data, and the GRU model shows the best performance with the highest prediction accuracy. The four ANN models outperform the ARMA model.",

keywords = "Artificial Neural Network, autoregressive moving average, gated recurrent unit, wind speed foresting",

author = "Uzair Zaman and Hamid Teimourzadeh and Sangani, \{Elias Hassani\} and Xiaodong Liang and Chung, \{Chi Yung\}",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE Electrical Power and Energy Conference, EPEC 2021 ; Conference date: 22-10-2021 Through 31-10-2021",

year = "2021",

month = nov,

doi = "10.1109/EPEC52095.2021.9621650",

language = "English",

series = "2021 IEEE Electrical Power and Energy Conference, EPEC 2021",

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

pages = "243--248",

booktitle = "2021 IEEE Electrical Power and Energy Conference, EPEC 2021",

}

Zaman, U, Teimourzadeh, H, Sangani, EH, Liang, X & Chung, CY 2021, Wind Speed Forecasting Using ARMA and Neural Network Models. in 2021 IEEE Electrical Power and Energy Conference, EPEC 2021. 2021 IEEE Electrical Power and Energy Conference, EPEC 2021, Institute of Electrical and Electronics Engineers Inc., pp. 243-248, 2021 IEEE Electrical Power and Energy Conference, EPEC 2021, Virtual, Online, Canada, 22/10/21. https://doi.org/10.1109/EPEC52095.2021.9621650

Wind Speed Forecasting Using ARMA and Neural Network Models. / Zaman, Uzair; Teimourzadeh, Hamid; Sangani, Elias Hassani et al.
2021 IEEE Electrical Power and Energy Conference, EPEC 2021. Institute of Electrical and Electronics Engineers Inc., 2021. p. 243-248 (2021 IEEE Electrical Power and Energy Conference, EPEC 2021).

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Wind Speed Forecasting Using ARMA and Neural Network Models

AU - Zaman, Uzair

AU - Teimourzadeh, Hamid

AU - Sangani, Elias Hassani

AU - Liang, Xiaodong

AU - Chung, Chi Yung

PY - 2021/11

Y1 - 2021/11

N2 - With the advancement of wind power generation technology, wind power plays an increasing role in modern power grids. To properly consider wind power for power systems planning and operation purpose, wind power and wind speed must be forecasted accurately. Wind is chaotic, random, irregular, and non-stationary in nature, which creates significant challenges in wind speed forecasting. This paper aims to forecast wind speed using both the statistical time series analysis method (autoregressive moving average (ARMA)) and neural network methods (feedforward neural network (FNN), recurrent neural network (RNN), long short-term memory (LSTM), and the gated recurrent unit (GRU)). The performance of the proposed five models is compared with the measured wind speed data, and the GRU model shows the best performance with the highest prediction accuracy. The four ANN models outperform the ARMA model.

AB - With the advancement of wind power generation technology, wind power plays an increasing role in modern power grids. To properly consider wind power for power systems planning and operation purpose, wind power and wind speed must be forecasted accurately. Wind is chaotic, random, irregular, and non-stationary in nature, which creates significant challenges in wind speed forecasting. This paper aims to forecast wind speed using both the statistical time series analysis method (autoregressive moving average (ARMA)) and neural network methods (feedforward neural network (FNN), recurrent neural network (RNN), long short-term memory (LSTM), and the gated recurrent unit (GRU)). The performance of the proposed five models is compared with the measured wind speed data, and the GRU model shows the best performance with the highest prediction accuracy. The four ANN models outperform the ARMA model.

KW - Artificial Neural Network

KW - autoregressive moving average

KW - gated recurrent unit

KW - wind speed foresting

UR - https://www.scopus.com/pages/publications/85123582304

U2 - 10.1109/EPEC52095.2021.9621650

DO - 10.1109/EPEC52095.2021.9621650

M3 - Conference article published in proceeding or book

AN - SCOPUS:85123582304

T3 - 2021 IEEE Electrical Power and Energy Conference, EPEC 2021

SP - 243

EP - 248

BT - 2021 IEEE Electrical Power and Energy Conference, EPEC 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2021 IEEE Electrical Power and Energy Conference, EPEC 2021

Y2 - 22 October 2021 through 31 October 2021

ER -

Wind Speed Forecasting Using ARMA and Neural Network Models

Abstract

Publication series

Conference

UN SDGs

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this