Key points are not available for this paper at this time.
In light of advancements in new technologies and the increasing complexity of power systems, this research addresses the critical challenge of predicting the stability of smart grids amid the rising adoption of renewable energy sources. The intermittent and unpredictable nature of renewables poses a significant obstacle to seamless integration, necessitating accurate stability predictions. This study focuses on developing a hybrid deep learning model, combining Multilayer Perceptron (MLP) and XGBoost classifiers, to effectively forecast smart grid stability under the Decentralized Smart Grid Control (DSGC) framework. Key evaluation metrics, including accuracy, precision, recall, F1-Score, ROC-AVC curve, and calibration plots, are employed for a comprehensive assessment and comparison with established classifiers.
Aliyeva et al. (Mon,) studied this question.