Fault classification and location identification in a smart DN using ANN and AMI with real-time data

• Main Authors: Muhammad Usama Usman, Juan Ospina, Md. Omar Faruque
• Format: Article
• Language: English
• Published: Wiley 2019-10-01
• Series: The Journal of Engineering
• Subjects: neural nets; fault diagnosis; smart meters; sensitivity analysis; fault location; smart power grids; distribution networks; power system simulation; power distribution faults; uoc; event-driven data; sms; novel ann-based fault classification; balanced fault types; unbalanced fault types; drts; fault resistance; classification accuracy; smart dn; ami; real-time data; real-time fault classification; smart distribution network; advanced metering infrastructure; real-time testing; simulated power system model; real-time simulator; communication network; dnp3 protocol; data concentrator; utility operations centre; location identification method; digital real-time simulator; transfer control protocol; internet protocol; comprehensive sensitivity analysis; noise level; loading conditions
• Online Access: https://digital-library.theiet.org/content/journals/10.1049/joe.2019.0896

This paper presents a real-time fault classification and location identification method for a smart distribution network (DN) using artificial neural networks (ANNs) and advanced metering infrastructure (AMI). It also describes the development of a testbed for real-time testing of the proposed approach. The testbed consists of a simulated power system model [running on a digital real-time simulator (DRTS)] and AMI. The core parts of AMI are smart meters (SMs), a communication network (developed using DNP3 protocol over transfer control protocol/Internet protocol), data concentrator (DC), and a Utility Operations Centre (UOC). Event-driven data from SMs are collected in the DC and then fed to the UOC for being used as inputs for the novel ANN-based fault classification and location identification algorithm. On the basis of the data received, the algorithm can classify the fault type and locate it with high accuracy. Both balanced and unbalanced fault types are tested on different nodes and lines throughout a DN modelled in offline and on the DRTS. A comprehensive sensitivity analysis is performed to validate the effectiveness of the proposed method. Classification accuracy of over 99% is achieved when classifying all fault types, and above 95% accuracy is achieved when identifying the fault location.