A New Approach to Electrical Fault Detection in Urban Structures Using Dynamic Programming and Optimized Support Vector Machines

Abstract

'Carlos Alejandro Espejo' 'Steffen Cantillo' 'Luis Gaviria' 'Jheifer Paez' 'Carlos Ochoa' 'Silvia Moreno' 'Claudet Polo' 'Roberto Pestana-Nobles' 'Camilo Montoya' 'Jiawei Xiang'] Electrical power systems are crucial, yet vulnerable, due to their complex and interconnected nature, necessitating effective fault detection and diagnostics to ensure stability and prevent disruptions. Advances in artificial intelligence (AI) and the Internet of Things (IoT) have transformed the ability to identify and resolve electrical system problems efficiently. Electrical systems operate at various scales, ranging from individual households to large-scale regional grids. In this study, we focus on medium-scale urban infrastructures. These environments present unique electrical challenges, such as phase imbalances and transient voltage fluctuations, which require robust fault detection mechanisms. This work investigates the use of AI with dynamic programming and a support vector machine (SVM) to improve fault detection. The data collected from voltage measurements in urban office buildings with smart meters over a period of six weeks was used to develop an AI model, demonstrating its applicability to similar urban infrastructures. This model achieved high accuracy in detecting system failures, identifying them with a performance greater than 99%, highlighting the potential of smart sensing technologies combined with AI to improve urban infrastructure management. The integration of smart sensors and advanced data analytics significantly increases the reliability and efficiency of energy systems, promoting sustainable and resilient urban environments.