Assessment and classification of grid stability with cost-sensitive stacked ensemble classifier

Smart Grid is an intelligent power grid with a bidirectional flow of electricity and information, that applies techniques to operate the autonomously near stability limit. An technique developed identify predict abnormalities due changes in customer behaviour unexpected disruption grid. A cost-sensitive stacked ensemble classifier (CS-SEC) proposed for predicting operations smart combines four base classifiers, namely Extreme gradient boosting, Naive Bayes, Nu-support vector machine Random forest at level-1 support as meta level-2. The uses probability prediction first-level classifiers stratified 5-fold cross-validation decentralized stability. achieved accuracy 98.6% specificity, recall precision 98.34%, 99.0% 99.06%, respectively. Extensive experimental evaluation results show CS-SEC provides accurate compared other state-of-the-art models. reveal robustness competency CS-SECs optimized parameters.