Estimation of Wake Effect in Wind Farms using Machine Learning Algorithms

Abstract

The need for renewable energy is always growing, making wind farm efficiency opti mization a vital area of study. Wind turbines that are dispersed throughout the landscape on wind farms use the kinetic energy of the wind to generate electricity. The idea that a wind turbine running in the wake of another turbine lowers wind speed after the rotor and reduces power generation is introduced by these massive wind farms with several turbines. The flow field in the wake of first row turbines is characterized by strong wind velocity deficit and high turbulent intensity as well. For this reason, a further downstream turbine in a wind farm can capture lesser wind energy than the first row turbine. Most importantly wake effect modeling is done in this study since it is important in determining the real en ergy production of a wind farm enhanced by this feature. In this study, machine learning algorithms are used to determine the wake effect of a wind turbine in a wind farm. Although the wind turbines appear simple in their working principle, their control is actually complex and difficult to maintain operational and structural integrity and performance. Each turbine produces a ‘wake’ when it takes wind energy; this is a major factor in the overall dynamics of the turbines. These wakes, which are areas of turbulent flow and decreased wind speed behind the turbines, are a major barrier to efficient wind energy harvesting. Moreover, the extension of the mechanical life of the turbines in not only increase efficiency but also sus tain turbulence in the wake. The present research work, specifically focuses on estimating wake effects in wind farms for machine learning algorithms. The data used for this aim is archival data of wind farm recordings, but in this case, the data is computationally syn thesized. The goal is to improve accuracy and efficacy while reducing wake estimating loss compared to traditional methods. Utilizing machine learning models such as Artificial Neural Networks (ANN), Random Forest Regression, Decision Tree Regression, Support Vector Machines (SVM)andtheadaptive neuro-fuzzy inference system (ANFIS) which are used to capture complex architecture and forecast accuracy. The outcomes of this research have the potential to revolutionize wind farm optimization by providing a more adaptive and faster wake estimation process. Among the models tested, the Random Forest Model performed the best with an outstanding R2 score of 0.99, demonstrating its effectiveness in accurately estimating wake effects. In comparison, the Decision Tree Regression also showed strong performance with R2 score of 0.97, although it exhibited a slightly higher MSEandRMSE