Machine Learning-Based Protection and Fault Identification of 100% Inverter-Based Microgrids

Aug 5, 2026

100% inverter-based renewable units are increasing in use, but they introduce major protection challenges for microgrids due to low fault currents and bidirectional power flows. The work addresses the gap in research by proposing machine learning (ML)-based protection using local electrical measurements to both detect and identify short-circuit faults. A decision tree analyzes a broad set of fault scenarios. PSCAD/EMTDC simulations generate training and testing data for a 100% inverter-based microgrid with four inverters, evaluated across seven fault types with varying fault resistance.

LanguageEnglish

CategoryTechnology

FormatPDF

Pages4

Reading Time10 min

AccessFree to download

Introduction

Motivation and protection challenges of 100% inverter-based microgrids

Limits of traditional protection and communication-based approaches

Prior work on ML-based fault diagnosis and microgrid protection

Machine Learning–Based Protection and Fault Identification of 100% Inverter-Based Microgrids Milad Beikbabaei, 1 Graduate Student Member, IEEE, Michael Lindemann,2 Graduate Student Member, IEEE, Mohammad Heidari Kapourchali,2 Member, IEEE, and Ali Mehrizi-Sani,1 Senior Member, IEEE 1 The Bradley Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA 24061 2 Department of Electrical Engineering, University of Alaska, Anchorage, AK 99508 [e-mails: miladb@vt.edu](e-mails: miladb@vt.edu), [mlindemann@alaska.edu](mlindemann@alaska.edu), [mhkapourchali@alaska.edu](mhkapourchali@alaska.edu), [mehrizi@vt.edu](mehrizi@vt.edu) arXiv :2405 .07310v1 [ ee ss . SY] 12 May 2024 Abstract—100% inverter-based renewable units are becoming more prevalent, introducing new challenges in the protection of microgrids that incorporate these resources. This is particularly due to low fault currents and bidirectional flows. Previous work has studied the protection of microgrids with high penetration of inverter-interfaced distributed generators; however, very few have studied the protection of a 100% inverter-based microgrid. This work proposes machine learning (ML)–based protection solutions using local electrical measurements that consider implementation challenges and effectively combine short-circuit fault detection and type identification. A decision tree method is used to analyze a wide range of fault scenarios. PSCAD/EMTDC simulation environment is used to create a dataset for training and testing the proposed method. The effectiveness of the proposed methods is examined under seven distinct fault types, each featuring varying fault resistance, in a 100% inverter-based microgrid consisting of four inverters. Index Terms—Fault identification, inverter-based resources (IBR), microgrid, protection. I. INTRODUCTION With the increasing prevalence of renewable energy resources in the form of inverter-based distributed generation units, traditional protection strategies for microgrids connecting multiple such resources may become insufficient. The protection of 100% inverter-based microgrids presents significant challenges [1], primarily due to the reduced inertia of inverterbased units [2] . A microgrid with low inertia sources could experience stability problems if line faults are not quickly cleared. In inverter-interfaced distributed generators, the current contribution is limited during short circuits, resulting in much lower fault currents. Limited fault current, combined with the bidirectional power flow and intermittent generation, © 20XX IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. This work of Virginia Tech is supported in part by the National Science Foundation (NSF) under award ECCS-1953213, in part by the State of Virginia’s Commonwealth Cyber Initiative ([www.cyberinitiative.org](www.cyberinitiative.org)), in part by the U.S. Department of Energy’s Office of Energy Efficiency and Renewable Energy (EERE) under the Solar Energy Technologies Office Award Number 38637 (UNIFI Consortium led by NREL), and in part by Manitoba Hydro International. The views expressed herein do not necessarily represent the views of the U.S. Department of Energy or the United States Government. The work of UAA is supported in part by the U.S. National Science Foundation (NSF) under awards OIA-2229772, RISE-2220624, RISE-2022705, and RISE- 2318385. presents a challenge for fault protection when employing traditional high fault current methods. Reference [3] studies the challenges faced when converting an existing distribution feeder to an inverter-based microgrid and suggests the use of ad

FAQs

Why is protection difficult in 100% inverter-based microgrids?

Protection is difficult because inverter-interfaced units contribute limited current during short circuits, leading to low fault currents. Low inertia and bidirectional power flow further complicate fast fault clearing and stability maintenance.

What protection approach does the document propose?

It proposes machine learning (ML)-based protection solutions using local electrical measurements. The method combines short-circuit fault detection with fault type identification.

How is the decision tree and dataset created and tested?

A decision tree method is used to analyze a wide range of fault scenarios. PSCAD/EMTDC simulations generate a dataset for training and testing, and effectiveness is examined under seven fault types with varying fault resistance in a four-inverter microgrid.

Aug 5, 2026

Upload by Genevieve