Modern Fault Diagnosis in Power Systems Based on 5G Networks

Abstract

The future power system will be dynamic, requiring Intelligent control, reliable protection, and fast communication. Modern concepts in power systems, such as smart grids, involve bidirectional power flow and two-way communication. Conventional protection schemes and fault diagnosis methods are unsuitable for future power systems. This study proposes a modern fault diagnosis that integrates 5G's reliable communication and AI. 5G's URLLC, mMTC, and edge computing can bring significant advantages to the applications of power systems. In this study, a concept of intelligent fault diagnosis is proposed, which utilizes a 5G network and AI. This work is divided into two main sections. The first section develops an ML-based power system protection model in MATLAB, and the second section deals with Simulating a 5G communication network is OMNeT ++. ML algorithm developed for power system protection achieved fault detection with an accuracy of 99% and isolated faults within 7ms. The standalone 5G network without an edge computing server achieved a round trip network latency of 20 ms.