Enhancing Power Grid Efficiency using Machine Learning Algorithms
Saadaldeen Rashid Ahmed, Leena Ali, Ali Jabbar Hussein, Bourair Al-Attar, Brwa Abdulrahman Abubaker, Jamal Fadhil Tawfeq, Abadal-Salam T. Hussain, Pritesh Shah
Abstract
This study tackles the important real-world topic of boosting power grid efficiency and reliability through the application of machine learning methods. Despite major developments in power grid management, issues exist in properly identifying events and improving system operations. Prior research has shown inadequacies in conventional procedures, driving our inquiry into innovative ways. We give a complete study employing a curated dataset encompassing power system assault scenarios and implementing several machine learning methods, including support vector machines (SVM), recurrent neural networks (RNN), decision trees (DT), and artificial neural networks (ANN). Our results reveal tremendous gains, with SVM reaching the greatest performance measures, including accuracy, precision, recall, F1-score, and ROC-AUC. This research adds to resolving current gaps in power grid optimization approaches, delivering practical insights for enhancing system resilience and efficiency in real-world applications.