Experimental Setup and Learning-Based AI Model for Developing Accurate PV Inverter Models: Preprint

Salma Bennai; Kumaraguru Prabakar; Yaswanth Nag Velaga; Subhankar Ganguly; Deepthi Vaidhynathan; Matthew Reynolds; Jonathan Frantz; Karthikeyan Balasubramaniam

Experimental Setup and Learning-Based AI Model for Developing Accurate PV Inverter Models: Preprint

Salma Bennai, Kumaraguru Prabakar, Yaswanth Nag Velaga, Subhankar Ganguly, Deepthi Vaidhynathan, Matthew Reynolds, Jonathan Frantz, Karthikeyan Balasubramaniam

Research output: Contribution to conference › Paper

Abstract

The integration of power electronics-based interfaces presents challenges due to the absence of detailed models and the high computational complexity. Generic models used in system studies lack accuracy in capturing converter dynamics. This paper proposes a data-driven approach developed from experimental setup data. This approach enhances accuracy in photovoltaic inverter modeling. We used two types of PV inverters in the experiment. The recorded experimental data undergo processing through a machine learning model. Results from the model trained through machine learning is also presented.

Original language	American English
Number of pages	9
State	Published - 2024
Event	IEEE Kansas Power & Energy Conference - Manhattan, Kansas Duration: 25 Apr 2024 → 26 Apr 2024

Conference

Conference	IEEE Kansas Power & Energy Conference
City	Manhattan, Kansas
Period	25/04/24 → 26/04/24

NREL Publication Number

NREL/CP-5D00-89562

Keywords

black box inverter modeling
co-simulation
electromagnetic transients simulation
inverter
inverter under test
machine learning-based modelling
photovoltaic

Access to Document

https://www.nrel.gov/docs/fy24osti/89562.pdf

Cite this

@conference{8700b12566b749f29889200ab594540b,

title = "Experimental Setup and Learning-Based AI Model for Developing Accurate PV Inverter Models: Preprint",

abstract = "The integration of power electronics-based interfaces presents challenges due to the absence of detailed models and the high computational complexity. Generic models used in system studies lack accuracy in capturing converter dynamics. This paper proposes a data-driven approach developed from experimental setup data. This approach enhances accuracy in photovoltaic inverter modeling. We used two types of PV inverters in the experiment. The recorded experimental data undergo processing through a machine learning model. Results from the model trained through machine learning is also presented.",

keywords = "black box inverter modeling, co-simulation, electromagnetic transients simulation, inverter, inverter under test, machine learning-based modelling, photovoltaic",

author = "Salma Bennai and Kumaraguru Prabakar and Velaga, {Yaswanth Nag} and Subhankar Ganguly and Deepthi Vaidhynathan and Matthew Reynolds and Jonathan Frantz and Karthikeyan Balasubramaniam",

year = "2024",

language = "American English",

note = "IEEE Kansas Power & Energy Conference ; Conference date: 25-04-2024 Through 26-04-2024",

}

TY - CONF

T1 - Experimental Setup and Learning-Based AI Model for Developing Accurate PV Inverter Models: Preprint

AU - Bennai, Salma

AU - Prabakar, Kumaraguru

AU - Velaga, Yaswanth Nag

AU - Ganguly, Subhankar

AU - Vaidhynathan, Deepthi

AU - Reynolds, Matthew

AU - Frantz, Jonathan

AU - Balasubramaniam, Karthikeyan

PY - 2024

Y1 - 2024

N2 - The integration of power electronics-based interfaces presents challenges due to the absence of detailed models and the high computational complexity. Generic models used in system studies lack accuracy in capturing converter dynamics. This paper proposes a data-driven approach developed from experimental setup data. This approach enhances accuracy in photovoltaic inverter modeling. We used two types of PV inverters in the experiment. The recorded experimental data undergo processing through a machine learning model. Results from the model trained through machine learning is also presented.

AB - The integration of power electronics-based interfaces presents challenges due to the absence of detailed models and the high computational complexity. Generic models used in system studies lack accuracy in capturing converter dynamics. This paper proposes a data-driven approach developed from experimental setup data. This approach enhances accuracy in photovoltaic inverter modeling. We used two types of PV inverters in the experiment. The recorded experimental data undergo processing through a machine learning model. Results from the model trained through machine learning is also presented.

KW - black box inverter modeling

KW - co-simulation

KW - electromagnetic transients simulation

KW - inverter

KW - inverter under test

KW - machine learning-based modelling

KW - photovoltaic

M3 - Paper

T2 - IEEE Kansas Power & Energy Conference

Y2 - 25 April 2024 through 26 April 2024

ER -

Experimental Setup and Learning-Based AI Model for Developing Accurate PV Inverter Models: Preprint

Abstract

Conference

NREL Publication Number

Keywords

Access to Document

Fingerprint

Cite this