Research

Paper

TESTING March 24, 2026

Scalable Impedance Identification of Diverse IBRs via Cluster-Specialized Neural Networks

Authors

Quang Manh Hoang, Guilherme Vieira Hollweg, Bang Nguyen, Akhtar Hussain, Wencong Su, Van-Hai Bui

Abstract

Modern machine learning approaches typically identify the impedance of a single inverter-based resource (IBR) and assume similar impedance characteristics across devices. In modern power systems, however, IBRs will employ diverse control topologies and algorithms, leading to highly heterogeneous impedance behaviors. Training one model per IBR is inefficient and does not scale. This paper proposes a scalable impedance identification framework for diverse IBRs via cluster-specialized neural networks. First, the dataset is partitioned into multiple clusters with similar feature profiles using the K-means clustering method. Then, each cluster is assigned a specialized feed-forward neural network (FNN) tailored to its characteristics, improving both accuracy and computational efficiency. In deployment, only a small number of measurements are required to predict impedance over a wide range of operating points. The framework is validated on six IBRs with varying control bandwidths, control structures, and operating conditions, and further tested on a previously unseen IBR using only ten measurement points. The results demonstrate high accuracy in both the clustering and prediction stages, confirming the effectiveness and scalability of the proposed method.

Metadata

arXiv ID: 2603.23203
Provider: ARXIV
Primary Category: eess.SY
Published: 2026-03-24
Fetched: 2026-03-25 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.23203v1</id>\n    <title>Scalable Impedance Identification of Diverse IBRs via Cluster-Specialized Neural Networks</title>\n    <updated>2026-03-24T13:51:00Z</updated>\n    <link href='https://arxiv.org/abs/2603.23203v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.23203v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Modern machine learning approaches typically identify the impedance of a single inverter-based resource (IBR) and assume similar impedance characteristics across devices. In modern power systems, however, IBRs will employ diverse control topologies and algorithms, leading to highly heterogeneous impedance behaviors. Training one model per IBR is inefficient and does not scale. This paper proposes a scalable impedance identification framework for diverse IBRs via cluster-specialized neural networks. First, the dataset is partitioned into multiple clusters with similar feature profiles using the K-means clustering method. Then, each cluster is assigned a specialized feed-forward neural network (FNN) tailored to its characteristics, improving both accuracy and computational efficiency. In deployment, only a small number of measurements are required to predict impedance over a wide range of operating points. The framework is validated on six IBRs with varying control bandwidths, control structures, and operating conditions, and further tested on a previously unseen IBR using only ten measurement points. The results demonstrate high accuracy in both the clustering and prediction stages, confirming the effectiveness and scalability of the proposed method.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='eess.SY'/>\n    <published>2026-03-24T13:51:00Z</published>\n    <arxiv:comment>This paper is accepted for presenting at IEEE PES General Meeting (PESGM) 2026. All the resources can be found here: https://github.com/ManhqhUMich12/Scalable-Impedance-Identification-of-Diverse-IBRs-via-Cluster-Specialized-Neural-Networ</arxiv:comment>\n    <arxiv:primary_category term='eess.SY'/>\n    <author>\n      <name>Quang Manh Hoang</name>\n    </author>\n    <author>\n      <name>Guilherme Vieira Hollweg</name>\n    </author>\n    <author>\n      <name>Bang Nguyen</name>\n    </author>\n    <author>\n      <name>Akhtar Hussain</name>\n    </author>\n    <author>\n      <name>Wencong Su</name>\n    </author>\n    <author>\n      <name>Van-Hai Bui</name>\n    </author>\n  </entry>"
}