Short-Term Wind Speed Prediction for Saudi Arabia via 1D-CNN

Abdulrahman Katranji; Md Shafiullah; Shafiqur Rehman

doi:10.1109/ICSET59111.2023.10295102

Short-Term Wind Speed Prediction for Saudi Arabia via 1D-CNN

Abdulrahman Katranji^*, Md Shafiullah, Shafiqur Rehman

^*Corresponding author for this work

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

2 Scopus citations

Abstract

As fluctuating wind power is incorporated into the energy mix, grid operators encounter dire challenges. Managing grid operations requires accurate knowledge of available wind power and its variation with time. Wind power can be estimated by providing reliable and fast wind speed prediction at different hub heights. Hence, this study proposes a one-dimensional convolutional neural network (1D-CNN) model for wind speed prediction at different heights and aboveground levels (AGL). The results of the proposed model are compared with three deep learning models to validate its repeatability. The results show a competitive performance between the proposed model and the gated recurrent unit (GRU) network. Furthermore, the study indicates that capturing wind speed at 18m height for training is sufficient for predicting wind speed at higher elevations. Further research could focus on adding exogenous variables to assess their impact on predicting wind speed at different AGL heights.

Original language	English
Title of host publication	ICSET 2023 - 2023 IEEE 13th International Conference on System Engineering and Technology, Proceeding
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	153-158
Number of pages	6
ISBN (Electronic)	9798350340891
DOIs	https://doi.org/10.1109/ICSET59111.2023.10295102
State	Published - 2023
Event	13th IEEE International Conference on System Engineering and Technology, ICSET 2023 - Shah Alam, Malaysia Duration: 2 Oct 2023 → …

Publication series

Name	ICSET 2023 - 2023 IEEE 13th International Conference on System Engineering and Technology, Proceeding

Conference

Conference	13th IEEE International Conference on System Engineering and Technology, ICSET 2023
Country/Territory	Malaysia
City	Shah Alam
Period	2/10/23 → …

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

convolutional neural networks
deep learning
recurrent neural networks
wind speed prediction

ASJC Scopus subject areas

Artificial Intelligence
Computer Science Applications
Electrical and Electronic Engineering
Media Technology
Instrumentation
Computer Vision and Pattern Recognition
Human-Computer Interaction
Information Systems

UN SDGs

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

Access to Document

10.1109/ICSET59111.2023.10295102

Cite this

Katranji, A., Shafiullah, M., & Rehman, S. (2023). Short-Term Wind Speed Prediction for Saudi Arabia via 1D-CNN. In ICSET 2023 - 2023 IEEE 13th International Conference on System Engineering and Technology, Proceeding (pp. 153-158). (ICSET 2023 - 2023 IEEE 13th International Conference on System Engineering and Technology, Proceeding). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICSET59111.2023.10295102

Katranji, Abdulrahman ; Shafiullah, Md ; Rehman, Shafiqur. / Short-Term Wind Speed Prediction for Saudi Arabia via 1D-CNN. ICSET 2023 - 2023 IEEE 13th International Conference on System Engineering and Technology, Proceeding. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 153-158 (ICSET 2023 - 2023 IEEE 13th International Conference on System Engineering and Technology, Proceeding).

@inproceedings{79574651f543417ebecbecb009358e4b,

title = "Short-Term Wind Speed Prediction for Saudi Arabia via 1D-CNN",

abstract = "As fluctuating wind power is incorporated into the energy mix, grid operators encounter dire challenges. Managing grid operations requires accurate knowledge of available wind power and its variation with time. Wind power can be estimated by providing reliable and fast wind speed prediction at different hub heights. Hence, this study proposes a one-dimensional convolutional neural network (1D-CNN) model for wind speed prediction at different heights and aboveground levels (AGL). The results of the proposed model are compared with three deep learning models to validate its repeatability. The results show a competitive performance between the proposed model and the gated recurrent unit (GRU) network. Furthermore, the study indicates that capturing wind speed at 18m height for training is sufficient for predicting wind speed at higher elevations. Further research could focus on adding exogenous variables to assess their impact on predicting wind speed at different AGL heights.",

keywords = "convolutional neural networks, deep learning, recurrent neural networks, wind speed prediction",

author = "Abdulrahman Katranji and Md Shafiullah and Shafiqur Rehman",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 13th IEEE International Conference on System Engineering and Technology, ICSET 2023 ; Conference date: 02-10-2023",

year = "2023",

doi = "10.1109/ICSET59111.2023.10295102",

language = "English",

series = "ICSET 2023 - 2023 IEEE 13th International Conference on System Engineering and Technology, Proceeding",

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

pages = "153--158",

booktitle = "ICSET 2023 - 2023 IEEE 13th International Conference on System Engineering and Technology, Proceeding",

address = "United States",

}

Katranji, A, Shafiullah, M & Rehman, S 2023, Short-Term Wind Speed Prediction for Saudi Arabia via 1D-CNN. in ICSET 2023 - 2023 IEEE 13th International Conference on System Engineering and Technology, Proceeding. ICSET 2023 - 2023 IEEE 13th International Conference on System Engineering and Technology, Proceeding, Institute of Electrical and Electronics Engineers Inc., pp. 153-158, 13th IEEE International Conference on System Engineering and Technology, ICSET 2023, Shah Alam, Malaysia, 2/10/23. https://doi.org/10.1109/ICSET59111.2023.10295102

Short-Term Wind Speed Prediction for Saudi Arabia via 1D-CNN. / Katranji, Abdulrahman; Shafiullah, Md ; Rehman, Shafiqur.
ICSET 2023 - 2023 IEEE 13th International Conference on System Engineering and Technology, Proceeding. Institute of Electrical and Electronics Engineers Inc., 2023. p. 153-158 (ICSET 2023 - 2023 IEEE 13th International Conference on System Engineering and Technology, Proceeding).

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

TY - GEN

T1 - Short-Term Wind Speed Prediction for Saudi Arabia via 1D-CNN

AU - Katranji, Abdulrahman

AU - Shafiullah, Md

AU - Rehman, Shafiqur

PY - 2023

Y1 - 2023

N2 - As fluctuating wind power is incorporated into the energy mix, grid operators encounter dire challenges. Managing grid operations requires accurate knowledge of available wind power and its variation with time. Wind power can be estimated by providing reliable and fast wind speed prediction at different hub heights. Hence, this study proposes a one-dimensional convolutional neural network (1D-CNN) model for wind speed prediction at different heights and aboveground levels (AGL). The results of the proposed model are compared with three deep learning models to validate its repeatability. The results show a competitive performance between the proposed model and the gated recurrent unit (GRU) network. Furthermore, the study indicates that capturing wind speed at 18m height for training is sufficient for predicting wind speed at higher elevations. Further research could focus on adding exogenous variables to assess their impact on predicting wind speed at different AGL heights.

AB - As fluctuating wind power is incorporated into the energy mix, grid operators encounter dire challenges. Managing grid operations requires accurate knowledge of available wind power and its variation with time. Wind power can be estimated by providing reliable and fast wind speed prediction at different hub heights. Hence, this study proposes a one-dimensional convolutional neural network (1D-CNN) model for wind speed prediction at different heights and aboveground levels (AGL). The results of the proposed model are compared with three deep learning models to validate its repeatability. The results show a competitive performance between the proposed model and the gated recurrent unit (GRU) network. Furthermore, the study indicates that capturing wind speed at 18m height for training is sufficient for predicting wind speed at higher elevations. Further research could focus on adding exogenous variables to assess their impact on predicting wind speed at different AGL heights.

KW - convolutional neural networks

KW - deep learning

KW - recurrent neural networks

KW - wind speed prediction

UR - https://www.scopus.com/pages/publications/85178041647

U2 - 10.1109/ICSET59111.2023.10295102

DO - 10.1109/ICSET59111.2023.10295102

M3 - Conference contribution

AN - SCOPUS:85178041647

T3 - ICSET 2023 - 2023 IEEE 13th International Conference on System Engineering and Technology, Proceeding

SP - 153

EP - 158

BT - ICSET 2023 - 2023 IEEE 13th International Conference on System Engineering and Technology, Proceeding

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 13th IEEE International Conference on System Engineering and Technology, ICSET 2023

Y2 - 2 October 2023

ER -

Katranji A, Shafiullah M , Rehman S. Short-Term Wind Speed Prediction for Saudi Arabia via 1D-CNN. In ICSET 2023 - 2023 IEEE 13th International Conference on System Engineering and Technology, Proceeding. Institute of Electrical and Electronics Engineers Inc. 2023. p. 153-158. (ICSET 2023 - 2023 IEEE 13th International Conference on System Engineering and Technology, Proceeding). doi: 10.1109/ICSET59111.2023.10295102

Short-Term Wind Speed Prediction for Saudi Arabia via 1D-CNN

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Fingerprint

Cite this