Deep graph temporal convolutional neural networks for short-term wind speed prediction

Jingjia Yu; Xin Liu; Lin Gong; Minxia Liu; Xi Xiang; Jian Xie; Yongyang Zhang

doi:10.1109/NNICE61279.2024.10498379

Deep graph temporal convolutional neural networks for short-term wind speed prediction

Jingjia Yu, Xin Liu^*, Lin Gong, Minxia Liu, Xi Xiang, Jian Xie, Yongyang Zhang

^*Corresponding author for this work

School of Mechanical Engineering

Beijing Institute of Technology

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

Abstract

Due to the high randomness of wind speed in the natural environment, accurate wind speed prediction is of great significance for wind energy. With the tremendous potential demonstrated by deep learning techniques in various fields, researchers have applied this technology to wind speed prediction and achieved promising results. In this paper, to improve the accuracy of wind speed prediction, a novel network called Graph Temporal Convolutional Network (GTCN) is proposed, which effectively exploits historical wind speed features from both temporal and spatial dimensions. Based on wind speed data collected from 11 turbines in a wind farm, five baseline models are used to conduct comparative studies. The results demonstrate that GTCN exhibits superior performance in wind speed prediction.

Original language	English
Title of host publication	2024 4th International Conference on Neural Networks, Information and Communication Engineering, NNICE 2024
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	213-216
Number of pages	4
ISBN (Electronic)	9798350394375
DOIs	https://doi.org/10.1109/NNICE61279.2024.10498379
Publication status	Published - 2024
Event	4th International Conference on Neural Networks, Information and Communication Engineering, NNICE 2024 - Hybrid, Guangzhou, China Duration: 19 Jan 2024 → 21 Jan 2024

Publication series

Name	2024 4th International Conference on Neural Networks, Information and Communication Engineering, NNICE 2024

Conference

Conference	4th International Conference on Neural Networks, Information and Communication Engineering, NNICE 2024
Country/Territory	China
City	Hybrid, Guangzhou
Period	19/01/24 → 21/01/24

Keywords

graph neural networks
temporal convolutional network
wind energy

Access to Document

10.1109/NNICE61279.2024.10498379

Cite this

Yu, J., Liu, X., Gong, L., Liu, M., Xiang, X., Xie, J., & Zhang, Y. (2024). Deep graph temporal convolutional neural networks for short-term wind speed prediction. In 2024 4th International Conference on Neural Networks, Information and Communication Engineering, NNICE 2024 (pp. 213-216). (2024 4th International Conference on Neural Networks, Information and Communication Engineering, NNICE 2024). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/NNICE61279.2024.10498379

Yu, Jingjia ; Liu, Xin ; Gong, Lin et al. / Deep graph temporal convolutional neural networks for short-term wind speed prediction. 2024 4th International Conference on Neural Networks, Information and Communication Engineering, NNICE 2024. Institute of Electrical and Electronics Engineers Inc., 2024. pp. 213-216 (2024 4th International Conference on Neural Networks, Information and Communication Engineering, NNICE 2024).

@inproceedings{527a9271ca7842af91ff256b9db8c395,

title = "Deep graph temporal convolutional neural networks for short-term wind speed prediction",

abstract = "Due to the high randomness of wind speed in the natural environment, accurate wind speed prediction is of great significance for wind energy. With the tremendous potential demonstrated by deep learning techniques in various fields, researchers have applied this technology to wind speed prediction and achieved promising results. In this paper, to improve the accuracy of wind speed prediction, a novel network called Graph Temporal Convolutional Network (GTCN) is proposed, which effectively exploits historical wind speed features from both temporal and spatial dimensions. Based on wind speed data collected from 11 turbines in a wind farm, five baseline models are used to conduct comparative studies. The results demonstrate that GTCN exhibits superior performance in wind speed prediction.",

keywords = "graph neural networks, temporal convolutional network, wind energy",

author = "Jingjia Yu and Xin Liu and Lin Gong and Minxia Liu and Xi Xiang and Jian Xie and Yongyang Zhang",

note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 4th International Conference on Neural Networks, Information and Communication Engineering, NNICE 2024 ; Conference date: 19-01-2024 Through 21-01-2024",

year = "2024",

doi = "10.1109/NNICE61279.2024.10498379",

language = "English",

series = "2024 4th International Conference on Neural Networks, Information and Communication Engineering, NNICE 2024",

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

pages = "213--216",

booktitle = "2024 4th International Conference on Neural Networks, Information and Communication Engineering, NNICE 2024",

address = "United States",

}

Yu, J, Liu, X, Gong, L, Liu, M, Xiang, X, Xie, J & Zhang, Y 2024, Deep graph temporal convolutional neural networks for short-term wind speed prediction. in 2024 4th International Conference on Neural Networks, Information and Communication Engineering, NNICE 2024. 2024 4th International Conference on Neural Networks, Information and Communication Engineering, NNICE 2024, Institute of Electrical and Electronics Engineers Inc., pp. 213-216, 4th International Conference on Neural Networks, Information and Communication Engineering, NNICE 2024, Hybrid, Guangzhou, China, 19/01/24. https://doi.org/10.1109/NNICE61279.2024.10498379

Deep graph temporal convolutional neural networks for short-term wind speed prediction. / Yu, Jingjia; Liu, Xin; Gong, Lin et al.
2024 4th International Conference on Neural Networks, Information and Communication Engineering, NNICE 2024. Institute of Electrical and Electronics Engineers Inc., 2024. p. 213-216 (2024 4th International Conference on Neural Networks, Information and Communication Engineering, NNICE 2024).

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

TY - GEN

T1 - Deep graph temporal convolutional neural networks for short-term wind speed prediction

AU - Yu, Jingjia

AU - Liu, Xin

AU - Gong, Lin

AU - Liu, Minxia

AU - Xiang, Xi

AU - Xie, Jian

AU - Zhang, Yongyang

PY - 2024

Y1 - 2024

N2 - Due to the high randomness of wind speed in the natural environment, accurate wind speed prediction is of great significance for wind energy. With the tremendous potential demonstrated by deep learning techniques in various fields, researchers have applied this technology to wind speed prediction and achieved promising results. In this paper, to improve the accuracy of wind speed prediction, a novel network called Graph Temporal Convolutional Network (GTCN) is proposed, which effectively exploits historical wind speed features from both temporal and spatial dimensions. Based on wind speed data collected from 11 turbines in a wind farm, five baseline models are used to conduct comparative studies. The results demonstrate that GTCN exhibits superior performance in wind speed prediction.

AB - Due to the high randomness of wind speed in the natural environment, accurate wind speed prediction is of great significance for wind energy. With the tremendous potential demonstrated by deep learning techniques in various fields, researchers have applied this technology to wind speed prediction and achieved promising results. In this paper, to improve the accuracy of wind speed prediction, a novel network called Graph Temporal Convolutional Network (GTCN) is proposed, which effectively exploits historical wind speed features from both temporal and spatial dimensions. Based on wind speed data collected from 11 turbines in a wind farm, five baseline models are used to conduct comparative studies. The results demonstrate that GTCN exhibits superior performance in wind speed prediction.

KW - graph neural networks

KW - temporal convolutional network

KW - wind energy

UR - http://www.scopus.com/inward/record.url?scp=85192524060&partnerID=8YFLogxK

U2 - 10.1109/NNICE61279.2024.10498379

DO - 10.1109/NNICE61279.2024.10498379

M3 - Conference contribution

AN - SCOPUS:85192524060

T3 - 2024 4th International Conference on Neural Networks, Information and Communication Engineering, NNICE 2024

SP - 213

EP - 216

BT - 2024 4th International Conference on Neural Networks, Information and Communication Engineering, NNICE 2024

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 4th International Conference on Neural Networks, Information and Communication Engineering, NNICE 2024

Y2 - 19 January 2024 through 21 January 2024

ER -

Yu J, Liu X, Gong L, Liu M, Xiang X, Xie J et al. Deep graph temporal convolutional neural networks for short-term wind speed prediction. In 2024 4th International Conference on Neural Networks, Information and Communication Engineering, NNICE 2024. Institute of Electrical and Electronics Engineers Inc. 2024. p. 213-216. (2024 4th International Conference on Neural Networks, Information and Communication Engineering, NNICE 2024). doi: 10.1109/NNICE61279.2024.10498379

Deep graph temporal convolutional neural networks for short-term wind speed prediction

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this