Testing the Wind Energy Data Based on Environmental Factors Predicted by Machine Learning with Analysis of Variance DOI Creative Commons
Yasemin Ayaz Atalan, Abdülkadir Atalan

Applied Sciences, Год журнала: 2024, Номер 15(1), С. 241 - 241

Опубликована: Дек. 30, 2024

This study proposes a two-stage methodology for predicting wind energy production using time, environmental, technical, and locational variables. In the first stage, machine learning algorithms, including random forest (RF), gradient boosting (GB), k-nearest neighbors (kNNs), linear regression (LR), decision trees (Tree), were employed to estimate output. Among these, RF exhibited best performance with lowest error metrics (MSE: 0.003, RMSE: 0.053) highest R2 value (0.988). second analysis of variance (ANOVA) was conducted evaluate statistical relationships between independent variables predicted dependent variable, identifying speed (p < 0.001) rotor as most influential factors. Furthermore, GB models produced predictions closely aligned actual data, achieving values 88.83% 89.30% in ANOVA validation phase. Integrating highlighted robustness methodology. These findings demonstrate integrating verification methods.

Язык: Английский

Testing the Wind Energy Data Based on Environmental Factors Predicted by Machine Learning with Analysis of Variance DOI Creative Commons
Yasemin Ayaz Atalan, Abdülkadir Atalan

Applied Sciences, Год журнала: 2024, Номер 15(1), С. 241 - 241

Опубликована: Дек. 30, 2024

This study proposes a two-stage methodology for predicting wind energy production using time, environmental, technical, and locational variables. In the first stage, machine learning algorithms, including random forest (RF), gradient boosting (GB), k-nearest neighbors (kNNs), linear regression (LR), decision trees (Tree), were employed to estimate output. Among these, RF exhibited best performance with lowest error metrics (MSE: 0.003, RMSE: 0.053) highest R2 value (0.988). second analysis of variance (ANOVA) was conducted evaluate statistical relationships between independent variables predicted dependent variable, identifying speed (p < 0.001) rotor as most influential factors. Furthermore, GB models produced predictions closely aligned actual data, achieving values 88.83% 89.30% in ANOVA validation phase. Integrating highlighted robustness methodology. These findings demonstrate integrating verification methods.

Язык: Английский

Процитировано

0