Wind speed prediction by utilizing geographic information system and machine learning approach: A case study of Karabük province in Türkiye DOI
Emrehan Gürsoy, Mehmet Gürdal, Engin Gedik

et al.

International Journal of Green Energy, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 17

Published: Dec. 22, 2024

This study analyzed wind speed data for years in Karabük province, Türkiye, using an Artificial Neural Network (ANN) with a Multilayer Perceptron (MLP) feed-forward network. The Bayesian Regularization algorithm was employed, well-known training Multi-Layer networks. investigated the relationship between and various meteorological parameters such as month, air temperature, relative humidity, pressure. results obtained from ANN model provided reliable methodology predicting future values province. To evaluate performance of model, metrics Mean Absolute Error (MAE), Average Relative Deviation (ARD), Squared (MSE), R-squared (R2) were utilized. demonstrated its efficacy by revealing highest average speeds 2.7 m/s Safranbolu province during August, corresponding MAE, ARD%, MSE, R2 −0.029, −0.380%, 0.0028, 0.999, respectively. maximum measured predicted Wind Speed (MWS) identified different months across locations, specifically August Eflani, July both Eskipazar CC September Safranbolu. Notably, recorded MWS observed at 42.8 July, while lowest 16.4 October. Besides, employing Geographic Information System (GIS) analysis, ranked districts, Safranbolu, Eskipazar, having to speeds,

Language: Английский

The Effect of Rotor Aspect Ratio, Stages, and Twist Angle on Savonius Wind Turbine Performance in Low Wind Speeds Environment DOI Creative Commons

Ivan Farozan,

Tubagus Ahmad Fauzi Soelaiman,

Priyono Soetikno

et al.

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 104041 - 104041

Published: Jan. 1, 2025

Language: Английский

Citations

2
Alarms management with fuzzy logic using wind turbine SCADA systems DOI Creative Commons
Fausto Pedro Garcı́a Márquez, Tahar Benmessaoud, Kamal Mohammedi

et al.

International Journal of Systems Assurance Engineering and Management, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 14, 2025

Abstract Supervisory Control and Data Acquisition (SCADA) systems are employed to collect data from sensors monitor the condition of wind turbines. Thresholds commonly used set alarms, generating many false downtimes, costs, etc. A real case study is presented validate approach. This paper proposes a novel approach based on Fuzzy Logic analyse main variables SCADA. Pearson’s correlation between reduce number that as inputs in system. The with perfect strong correlations have been selected signal studied by considering difference moving average value because it shows if close or not conditions free faults. thresholds cluster into three groups statistical analysis new variables, i.e., obtained value. helps decrease alarms using capable processing large datasets online. results validated employing SVM, where MAPE analysed both methods.

Language: Английский

Citations

0
A modified sine–cosine probability distribution: Its mathematical features with statistical modeling in sports and reliability prospects DOI
Liang Kong, Jiaojiao Liu,

Nader Al-Rashidi

et al.

Alexandria Engineering Journal, Journal Year: 2025, Volume and Issue: 121, P. 414 - 425

Published: March 5, 2025

Language: Английский

Citations

0
Green hydrogen production from wind energy in Far Eastern Federal District (FEFD), the Russian Federation DOI Creative Commons

Mihail Demidionov

Regional Sustainability, Journal Year: 2025, Volume and Issue: 6(1), P. 100199 - 100199

Published: Feb. 1, 2025

Language: Английский

Citations

0
Comparative Analysis of Five Numerical Methods and the Whale Optimization Algorithm for Wind Potential Assessment: A Case Study in Whittlesea, Eastern Cape, South Africa DOI Open Access
Ngwarai Shambira, Lwando Luvatsha, Patrick Mukumba

et al.

Processes, Journal Year: 2025, Volume and Issue: 13(5), P. 1344 - 1344

Published: April 27, 2025

This study explores the potential of wind energy to address electricity shortages in South Africa, focusing on Ekuphumleni community Whittlesea. Given challenges expanding national grid these areas, is considered be a feasible alternative provide clean, renewable and reduce fossil fuel dependence this community. research evaluates utilizing two-parameter Weibull distribution, with scale shape parameters estimated by five traditional numerical methods one metaheuristic optimization technique: whale algorithm (WOA). Goodness-of-fit tests, such as coefficient determination (R2) power density error (WPDE), were utilized determine best method for accurately estimating parameters. Furthermore, net fitness, which combines R2 WPDE, was employed holistic assessment overall performance. Whittlesea showed moderate speeds, averaging 3.88 m/s at 10 m above ground level (AGL), highest speeds winter (4.87 m/s) optimum July. The WOA outperformed all distribution Interestingly, openwind (OWM), technique based iterative methods, Brent comparable performance WOA. 67.29 W/m2, categorizing Whittlesea’s poor suitable small-scale turbines. east patterns favor efficient turbine placement. recommends using augmented turbines site maximize capture speeds.

Language: Английский

Citations

0
Evaluation of genetic algorithm alternatives for wind speed modeling using grey relational analysis DOI Creative Commons
H. Gürgüç Işık,

Muhammet Burak Kılıç

Journal of Engineering and Applied Science, Journal Year: 2025, Volume and Issue: 72(1)

Published: April 29, 2025

Abstract Wind speed modeling is a crucial tool for the use of sustainable energy by reducing fossil fuel dependence. This implies efficiency wind turbine and assessment potential renewable development. Weibull distribution commonly used in due to its flexibility effectiveness determine patterns. Therefore, this paper focuses on parameter estimates using genetic algorithm (GA) optimization based maximum likelihood (ML) method. study addresses evaluation different fitness functions selection GA sets, including population size, crossover rate, mutation rate. The proposed function provides estimate shape distribution. alternatives method are evaluated Kolmogorov–Smirnov (KS), coefficient determination (R 2 ), root mean square error (RMSE), Akaike information criterion, Bayesian power density (PDE) over three datasets. grey relational analysis ranking alternatives. best alternative also compared particle swarm estimation satisfactory results R , RMSE, PDE. A simulation performed evaluate performances with respect deficiency criterion. Finally, we recommend 1 3 estimation; these contribute sets practice.

Language: Английский

Citations

0
Analysis of wind power generation potential and wind turbine installation economics: A correlation-based approach DOI Creative Commons
Amit Yadav,

Vibha Yadav,

U. Chaithanya Kumar

et al.

Results in Engineering, Journal Year: 2024, Volume and Issue: unknown, P. 103743 - 103743

Published: Dec. 1, 2024

Language: Английский

Citations

2
A Fast Real-Time Transient Stability Estimation for Enhanced Situational Awareness DOI
Divya Rishi Shrivastava, Shahbaz Ahmed Siddiqui, Hasmat Malik

et al.

Advances in intelligent systems and computing, Journal Year: 2024, Volume and Issue: unknown, P. 291 - 301

Published: Jan. 1, 2024

Language: Английский

Citations

0
Wind speed prediction by utilizing geographic information system and machine learning approach: A case study of Karabük province in Türkiye DOI
Emrehan Gürsoy, Mehmet Gürdal, Engin Gedik

et al.

International Journal of Green Energy, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 17

Published: Dec. 22, 2024

This study analyzed wind speed data for years in Karabük province, Türkiye, using an Artificial Neural Network (ANN) with a Multilayer Perceptron (MLP) feed-forward network. The Bayesian Regularization algorithm was employed, well-known training Multi-Layer networks. investigated the relationship between and various meteorological parameters such as month, air temperature, relative humidity, pressure. results obtained from ANN model provided reliable methodology predicting future values province. To evaluate performance of model, metrics Mean Absolute Error (MAE), Average Relative Deviation (ARD), Squared (MSE), R-squared (R2) were utilized. demonstrated its efficacy by revealing highest average speeds 2.7 m/s Safranbolu province during August, corresponding MAE, ARD%, MSE, R2 −0.029, −0.380%, 0.0028, 0.999, respectively. maximum measured predicted Wind Speed (MWS) identified different months across locations, specifically August Eflani, July both Eskipazar CC September Safranbolu. Notably, recorded MWS observed at 42.8 July, while lowest 16.4 October. Besides, employing Geographic Information System (GIS) analysis, ranked districts, Safranbolu, Eskipazar, having to speeds,

Language: Английский

Citations

0