ABSTRACT
Wind farm layout optimization that considers the wake effect is crucial to improve the power generation and wind energy efficiency of a wind farm. In this study, a state-of-the-art three-dimensional (3D) wake model is used to optimize the layout of wind turbines (WTs) in a wind farm. A surrogate model based on a back propagation neural network(BPNN) is developed to simplify the complex process of calculating the wake deficits. Furthermore, discrete particle swarm algorithm is used for optimizing the wind farm layout while considering different hub heights. The results show that the surrogate model significantly reduces the computation time. The optimization of the layout of WTs with different hub heights in a wind farm substantially reduces the wake effect.
Acknowledgments
We appreciate the support from the National Natural Science Foundation of China (Project No. 21676086).
Disclosure statement
No potential conflict of interest was reported by the author(s).