Wind Farm Power Prediction Considering Layout and Wake Effect: Case Study of Saudi Arabia

Khadijah Barashid, Amr Munshi () and Ahmad Alhindi
Additional contact information
Khadijah Barashid: Computer Science Department, Umm Al-Qura University, Makkah 24211, Saudi Arabia
Amr Munshi: Computer Engineering Department, Umm Al-Qura University, Makkah 24382, Saudi Arabia
Ahmad Alhindi: Computer Science Department, Umm Al-Qura University, Makkah 24211, Saudi Arabia

Energies, 2023, vol. 16, issue 2, 1-22

Abstract: The world’s technological and economic advancements have led to a sharp increase in the demand for electrical energy. Saudi Arabia is experiencing rapid economic and demographic growth, which is resulting in higher energy needs. The limits of fossil fuel reserves and their disruption to the environment have motivated the pursuit of alternative energy options such as wind energy. In order to regulate the power system to maintain safe and dependable operation, projections of current and daily power generation are crucial. Thus, this work focuses on wind power prediction and the statistical analysis of wind characteristics using wind data from a meteorological station in Makkah, Saudi Arabia. The data were collected over four years from January 2015 to July 2018. More than twelve thousand data points were collected and analyzed. Layout and wake effect studies were carried out. Furthermore, the near wake length downstream from the rotor disc between 1 and 5 rotor diameters (1D to 5D) was taken into account. Five robust machine learning algorithms were implemented to estimate the potential wind power production from a wind farm in Makkah, Saudi Arabia. The relationship between the wind speed and power produced for each season was carefully studied. Due to the variability in the wind speeds, the power production fluctuated much more in the winter. The higher the wind speed, the more significant the difference in energy production between the five farm layouts, and vice versa, whereas at a low wind speed, there was no significant difference in the power production in all of the near wake lengths of the 1D to 5D rotor diameters downstream from the rotor disc. Among the utilized prediction models, the decision tree regression was found to have the best accuracy values in all four utilized evaluation metrics, with 0.994 in R-squared, 0.025 in MAE, 0.273 in MSE, and 0.522 in RMSE. The obtained results were satisfactory and provide support for the construction of several wind farms, producing hundreds of megawatts, in Saudi Arabia, particularly in the Makkah Region.

Keywords: wind power; renewable energy; machine learning; regression; wake effect; wind energy (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/16/2/938/pdf (application/pdf)
https://www.mdpi.com/1996-1073/16/2/938/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:16:y:2023:i:2:p:938-:d:1035581

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().