Abstract:
The global demand for energy is rapidly rising. As a result, energy systems must evolve and be
upgraded in order to become more efficient, adaptable, and sustainable. A smart grid reduces
workforce while providing consumers with safe, reliable, high-quality, and long-lasting
electricity. Smart grids use digital communication technology to enable two-way flow of
electricity and data. This vast amount of data needs to be processed for making better decisions
for maintaining the grid stability. ML and AI approaches are utilised to acquire, store, and
manage this data. This study compares the performance of modern machine learning methods for
predicting smart grid stability. The dataset that was chosen contains findings from a smart grid
simulation. XGBoost, Adaboost, Gradient Boosting Method (GBM), HistGBM, LightGBM and
CatBoost algorithms have been implemented to forecast smart grid stability. Performance of the
ML model has been evaluated based on Classification evaluation metrics. The following
evaluation metrics such as accuracy, precision, recall, F1-score, MCC, specificity, training time,
predicting time, AUC-ROC curve and AUC-PR CURVE are used for classification
evaluation.An efficient Stacking Ensemble Classifier (SEC) model developed by using the above
mentioned machine learning algorithms and compared the evaluated results of individual
machine learning models with the SEC model.
