Neuro-physical dynamic load modeling using differentiable parametric optimization

TL;DR

This paper introduces a neuro-physical load modeling approach combining traditional ZIP models with neural networks, trained via differentiable programming, to improve transient stability analysis in distribution systems.

Contribution

It presents a novel differentiable programming framework for training neuro-physical load models that enhance transient stability analysis accuracy.

Findings

Effective modeling of distribution system loads using neuro-physical models

Improved accuracy over traditional load models in stability analysis

Demonstrated on a 350-bus network

Abstract

In this work, we investigate a data-driven approach for obtaining a reduced equivalent load model of distribution systems for electromechanical transient stability analysis. The proposed reduced equivalent is a neuro-physical model comprising of a traditional ZIP load model augmented with a neural network. This neuro-physical model is trained through differentiable programming. We discuss the formulation, modeling details, and training of the proposed model set up as a differential parametric program. The performance and accuracy of this neurophysical ZIP load model is presented on a medium-scale 350-bus transmission-distribution network.