Key points are not available for this paper at this time.
In response to the challenges faced by the power grid in Guangxi, China during the peak winter demand exacerbated by the impact of cold wave weather, this study proposes a method for short-term wind power prediction under cold wave conditions. Firstly, the TimeGAN model is employed to augment the limited dataset under cold wave climates, enhancing the adaptability of the model to such weather conditions. Secondly, the cold wave weather is categorized into three scenarios: strong winds, low temperatures with ice covering, and intense rainfall. Neural Prophet models are then utilized separately for predicting each scenario. The proposed models are validated using wind power data from a wind farm in Guangxi, demonstrating excellent predictive performance under cold wave weather conditions.
Hu et al. (Fri,) studied this question.