Wind energy is a cornerstone of the global transition to renewable and sustainable energy systems. However, the same meteorological processes that generate this clean energy can also produce extreme wind events that threaten the structural integrity and operational reliability of wind turbines and power grids. Therefore, accurately predicting extreme wind speeds is a critical link between promoting clean energy and ensuring infrastructure resilience. Traditional models often struggle to capture the multimodal characteristics of extreme wind speeds under complex meteorological conditions due to fixed distribution assumptions or unstable training of mixture models, leading to estimation biases that undermine planning reliability and may result in catastrophic turbine failures or overly conservative designs. To address these issues—particularly weight imbalance and overfitting–this study proposes an enhanced regularized extreme value mixture model (ERDC-EVMM). This method integrates elastic network regularization and Kullback–Leibler divergence constraints within a Mixture of Experts framework, and employs K-means initialization and momentum-based training to enhance convergence stability. Validated using daily extreme wind speed sequences from coastal and inland wind farms, the model outperforms standard GEV and mixture models in terms of goodness-of-fit, percentile accuracy, and return period estimates, while achieving a convergence speed that is more than 30% faster (82 iterations). By balancing accuracy and training stability, the ERDC-EVMM model provides a reliable statistical tool for extreme wind speed forecasting, supporting the safe expansion of wind energy infrastructure and the design of climate-resilient communities.
LIU et al. (Sat,) studied this question.