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

TL;DR

This paper introduces a scalable neural network framework that clusters diverse inverter-based resources and employs specialized models for accurate impedance identification across various device types and operating conditions.

Contribution

It proposes a novel cluster-specialized neural network approach that improves scalability and accuracy in impedance identification for heterogeneous IBRs.

Findings

High accuracy in impedance prediction across multiple IBRs

Effective clustering of diverse IBRs using K-means

Successful generalization to unseen IBRs with limited measurements

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.