时间：2024年12月17日 14：00-14:30
地点：民主楼313
报告人：梁铮
报告标题：An Improved Fault Ride-Through Strategy for Renewable Power Plants Considering Collector Line Characteristics
报告摘要：With the continuous growth in the installed capacity of renewable power plants, the transient dynamics of power systems, which incorporate a high proportion of renewable energy and power electronic devices, are becoming increasingly complex. This complexity raises the risk of voltage instability during faults at renewable power plants, posing a serious threat to the safe and stable operation of power systems. To address these challenges, this paper establishes an equivalent model of renewable power plants to study the impact of collector line parameters on fault ride-through (FRT) performance. Subsequently, a FRT strategy for renewable power plants considering collector lines is proposed. Furthermore, to address the issue of uncertain line parameters in renewable power plants, Koopman theory is applied to achieve high-dimensional linearization of low-dimensional functions. The collector line parameters for the renewable power plants are obtained by utilizing actual operational data as samples. Finally, electromagnetic transient simulations are conducted in PSCAD to verify the improved voltage support performance of the proposed FRT strategy.
时间：2024年12月17日14:30-15:00
地点：民主楼313
报告人：王湘婷
报告标题：Multimodal Ultra-Short-Term Irradiance Forecasting Based on Sky Images: Exploring the Complementary Characteristics of Clouds and Irradiance
报告摘要：The high uncertainty in solar irradiance changes limits its application in power grids. Data-driven research that integrates sky images and irradiance has made significant advances. However, there has been limited attention to the impact of different fusion methods for sky images on prediction performance. We propose a novel multi-modal interaction fusion framework aimed at extracting complementary correlations between these two heterogeneous data sources to improve the accuracy of predicting critical ramp events. First, 3D-ResNet and Informer are used to encode the spatial features of sky images and the temporal features of irradiance, respectively. An interaction matrix is then constructed to fuse these two modalities, ultimately generating solar irradiance predictions. Experimental results show that, compared to state-of-the-art baseline models, the proposed method reduces RMSE by 20.9%, enhancing the model's ability to leverage information from sky images.
