Optimal Placement of Wind Power System Using Machine Learning

The switch from fossil fuels to sustainable energy sources is crucial for power generation sustainability. Hence, this study, proposed a plan for the installation of wind turbines in Doha Qatar, and forecasted the future temperature and wind speed for the optimal placement of large-scale wind turbi...

Full description

Saved in:
Bibliographic Details
Main Authors: Abdul Karim, Muhammad Amir Raza, Darakhshan Ara, Muhammad Shahid, Shakir Ali Soomro
Format: Article
Language:English
Published: Sir Syed University of Engineering and Technology, Karachi. 2025-06-01
Series:Sir Syed University Research Journal of Engineering and Technology
Online Access:https://sirsyeduniversity.edu.pk/ssurj/rj/index.php/ssurj/article/view/679
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849428752620060672
author Abdul Karim
Muhammad Amir Raza
Darakhshan Ara
Muhammad Shahid
Shakir Ali Soomro
author_facet Abdul Karim
Muhammad Amir Raza
Darakhshan Ara
Muhammad Shahid
Shakir Ali Soomro
author_sort Abdul Karim
collection DOAJ
description The switch from fossil fuels to sustainable energy sources is crucial for power generation sustainability. Hence, this study, proposed a plan for the installation of wind turbines in Doha Qatar, and forecasted the future temperature and wind speed for the optimal placement of large-scale wind turbines using the Pythons algorithms namely, Long Short-Term Memory (LSTM), Prophet (PT), Support Vector Regression (SVR), Linear Regression (LR), Seasonal Autoregressive Integrated Moving Average with External Factors (SARIMAX), and K-Nearest Neighbors (KNN). These models have taken raw data from 2000 to 2019 and tested from 2020 to 2023 and finally predict the future from 2023 to 2030. The results show that for renewable energy variables such as temperature and wind speed, statistical models such as SARIMAX perform better than traditional models such as LSTM, PT, SVR, LR, and KNN. Because SARIMAX captures long-term dependencies, it is particularly suitable for time series data where past events have a large impact on future values. It is recommended that wind power has enormous potential and offers a low-carbon future for Doha Qatar.
format Article
id doaj-art-077b20d466da49259fce7b4e07f6da56
institution Kabale University
issn 1997-0641
2415-2048
language English
publishDate 2025-06-01
publisher Sir Syed University of Engineering and Technology, Karachi.
record_format Article
series Sir Syed University Research Journal of Engineering and Technology
spelling doaj-art-077b20d466da49259fce7b4e07f6da562025-08-20T03:28:37ZengSir Syed University of Engineering and Technology, Karachi.Sir Syed University Research Journal of Engineering and Technology1997-06412415-20482025-06-0115110.33317/ssurj.679Optimal Placement of Wind Power System Using Machine LearningAbdul Karim0Muhammad Amir Raza1Darakhshan Ara2Muhammad Shahid3Shakir Ali Soomro4Department of Electrical Engineering Mehran University of Engineering and Technology, SZAB Campus Khairpur Mirs’ Sindh PakistanMUETDepartment of Basic Sciences and Humanities, Dawood University of Engineering and Technology. Karachi, PakistanDepartment of Electronic Engineering, Dawood University of Engineering and Technology, Karachi, PakistanDepartment of Electrical Engineering Mehran University of Engineering and Technology, SZAB Campus Khairpur Mirs’ Sindh Pakistan The switch from fossil fuels to sustainable energy sources is crucial for power generation sustainability. Hence, this study, proposed a plan for the installation of wind turbines in Doha Qatar, and forecasted the future temperature and wind speed for the optimal placement of large-scale wind turbines using the Pythons algorithms namely, Long Short-Term Memory (LSTM), Prophet (PT), Support Vector Regression (SVR), Linear Regression (LR), Seasonal Autoregressive Integrated Moving Average with External Factors (SARIMAX), and K-Nearest Neighbors (KNN). These models have taken raw data from 2000 to 2019 and tested from 2020 to 2023 and finally predict the future from 2023 to 2030. The results show that for renewable energy variables such as temperature and wind speed, statistical models such as SARIMAX perform better than traditional models such as LSTM, PT, SVR, LR, and KNN. Because SARIMAX captures long-term dependencies, it is particularly suitable for time series data where past events have a large impact on future values. It is recommended that wind power has enormous potential and offers a low-carbon future for Doha Qatar. https://sirsyeduniversity.edu.pk/ssurj/rj/index.php/ssurj/article/view/679
spellingShingle Abdul Karim
Muhammad Amir Raza
Darakhshan Ara
Muhammad Shahid
Shakir Ali Soomro
Optimal Placement of Wind Power System Using Machine Learning
Sir Syed University Research Journal of Engineering and Technology
title Optimal Placement of Wind Power System Using Machine Learning
title_full Optimal Placement of Wind Power System Using Machine Learning
title_fullStr Optimal Placement of Wind Power System Using Machine Learning
title_full_unstemmed Optimal Placement of Wind Power System Using Machine Learning
title_short Optimal Placement of Wind Power System Using Machine Learning
title_sort optimal placement of wind power system using machine learning
url https://sirsyeduniversity.edu.pk/ssurj/rj/index.php/ssurj/article/view/679
work_keys_str_mv AT abdulkarim optimalplacementofwindpowersystemusingmachinelearning
AT muhammadamirraza optimalplacementofwindpowersystemusingmachinelearning
AT darakhshanara optimalplacementofwindpowersystemusingmachinelearning
AT muhammadshahid optimalplacementofwindpowersystemusingmachinelearning
AT shakiralisoomro optimalplacementofwindpowersystemusingmachinelearning