article · PLoS ONE
This research evaluates multiple machine learning and deep learning algorithms to predict wind turbine power output from environmental conditions, including wind speed, wind direction, temperature, and humidity. Using a dataset containing 40,000 observations, the models were assessed through standard error and correlation metrics. Among traditional machine learning techniques, Extra Trees delivered the strongest results, reaching an R-squared value of 0.7231. Among deep learning approaches, an Artificial Neural Network performed best, slightly outperforming the tree-based method with an R-squared of 0.7248. The deep learning models demonstrated a superior capability for capturing non-linear relationships across multivariate data. Furthermore, applying preprocessing methods such as feature scaling alongside hyperparameter tuning boosted accuracy across the board, providing measurable performance improvements over previous benchmark results.
Wind power generation fluctuates constantly with changing weather conditions. Accurate forecasting of turbine electricity generation helps grid operators balance power supply and demand. By demonstrating that computational models can reliably forecast power output from variables like wind speed, humidity, and temperature, this research supports more effective planning and management of renewable energy networks.
This work could enable software tools for wind farm operators and energy grid managers seeking to optimise power dispatch and forecasting. Because the models were tested on an empirical dataset of 40,000 observations, the research sits at an applied algorithmic stage, requiring integration into industrial management platforms or supervisory control systems before operational deployment.
AI-generated from the published abstract. Always read the original work before citing.
This study presents a comprehensive comparative analysis of Machine Learning (ML) and Deep Learning (DL) models for predicting Wind Turbine (WT) power output based on environmental variables such as temperature, humidity, wind speed, and wind direction. Along with Artificial Neural Network (ANN), Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN), and Convolutional Neural Network (CNN), the following ML models were looked at: Linear Regression (LR), Support Vector Regressor (SVR), Random Forest (RF), Extra Trees (ET), Adaptive Boosting (AdaBoost), Categorical Boosting (CatBoost), Extreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM). Using a dataset of 40,000 observations, the models were assessed based on R-squared, Mean Absolute Error (MAE), and Root Mean Square Error (RMSE). ET achieved the highest performance among ML models, with an R-squared value of 0.7231 and a RMSE of 0.1512. Among DL models, ANN demonstrated the best performance, achieving an R-squared value of 0.7248 and a RMSE of 0.1516. The results show that DL models, especially ANN, did slightly better than the best ML models. This means that they are better at modeling non-linear dependencies in multivariate data. Preprocessing techniques, including feature scaling and parameter tuning, improved model performance by enhancing data consistency and optimizing hyperparameters. When compared to previous benchmarks, the performance of both ANN and ET demonstrates significant predictive accuracy gains in WT power output forecasting. This study's novelty lies in directly comparing a diverse range of ML and DL algorithms while highlighting the potential of advanced computational approaches for renewable energy optimization.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1371/journal.pone.0317619
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
