Smart Grid Fault Detection and Restoration Using Artificial Intelligence and Edge Computing
Abstract
The increasing complexity of modern power distribution networks and the integration of renewable energy sources require intelligent and reliable fault management systems. This paper presents , a smart grid framework that integrates Artificial Intelligence (AI) and edge computing for real-time fault detection, prediction, and restoration. The proposed system continuously monitors electrical parameters such as voltage, current, and power using sensors. Edge-based processing enables rapid identification of abnormal conditions and facilitates automated fault isolation and power rerouting through relay-based switching. Machine learning techniques are incorporated to analyze historical and real-time data for fault classification and predictive maintenance. A NodeMCU (ESP8266) module enables remote monitoring and real-time fault notifications through Telegram, while an LCD provides local visualization of grid parameters and system status. The proposed approach aims to reduce fault detection time, minimize power interruptions, improve maintenance efficiency, and enhance the reliability and resilience of smart grid networks
