Low-Cost Hardware Platform for Testing ML-Based Edge Power Grid Oscillation Detectors

Sergio A. Dorado-Rojas; Shunyao Xu; Luigi Vanfretti; Galilea Olvera; M. Ilies I. Ayachi; Shehab Ahmed

doi:10.1109/MSCPES55116.2022.9770146

Low-Cost Hardware Platform for Testing ML-Based Edge Power Grid Oscillation Detectors

Sergio A. Dorado-Rojas, Shunyao Xu, Luigi Vanfretti, Galilea Olvera, M. Ilies I. Ayachi, Shehab Ahmed

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

Abstract

This paper introduces a low-cost hardware testing platform designed to investigate the performance of a Machine Learning (ML)-based edge application developed to detect forced oscillations in power grids. The core of the ML application lies in a Convolutional Neural Network (CNN) model deployed on an ML edge device (NVIDIA Jetson TX2). The proposed platform consists of a method for real-time signal emulation using the WaveForms Software Development Kit (SDK) that defines low-voltage signals generated by Digilent's Analog Discovery Board. The output of the signal generator is read by the Jetson board using an Analog-to-Digital Converter (ADC). Our experiments compare the performance of different ADCs when performing inference with the same CNN model. Additionally, we give an overview of the communication scheme that allows experiment automation, which is particularly useful when experiment design is time-consuming and laborious.

Original language	English (US)
Title of host publication	2022 10th Workshop on Modelling and Simulation of Cyber-Physical Energy Systems, MSCPES 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665468657
DOIs	https://doi.org/10.1109/MSCPES55116.2022.9770146
State	Published - 2022
Event	10th Workshop on Modelling and Simulation of Cyber-Physical Energy Systems, MSCPES 2022 - Milan, Italy Duration: May 3 2022 → …

Publication series

Name	2022 10th Workshop on Modelling and Simulation of Cyber-Physical Energy Systems, MSCPES 2022

Conference

Conference	10th Workshop on Modelling and Simulation of Cyber-Physical Energy Systems, MSCPES 2022
Country/Territory	Italy
City	Milan
Period	05/3/22 → …

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

Convolutional Neural Network
Data Acquisition
Experiment Automation
Forced Oscillations
Real-Time Signal Emulation

ASJC Scopus subject areas

Energy Engineering and Power Technology
Renewable Energy, Sustainability and the Environment
Modeling and Simulation
Computer Networks and Communications
Information Systems and Management

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/MSCPES55116.2022.9770146

Cite this

Dorado-Rojas, S. A., Xu, S., Vanfretti, L., Olvera, G., Ayachi, M. I. I., & Ahmed, S. (2022). Low-Cost Hardware Platform for Testing ML-Based Edge Power Grid Oscillation Detectors. In 2022 10th Workshop on Modelling and Simulation of Cyber-Physical Energy Systems, MSCPES 2022 (2022 10th Workshop on Modelling and Simulation of Cyber-Physical Energy Systems, MSCPES 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MSCPES55116.2022.9770146

Dorado-Rojas, Sergio A. ; Xu, Shunyao ; Vanfretti, Luigi et al. / Low-Cost Hardware Platform for Testing ML-Based Edge Power Grid Oscillation Detectors. 2022 10th Workshop on Modelling and Simulation of Cyber-Physical Energy Systems, MSCPES 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (2022 10th Workshop on Modelling and Simulation of Cyber-Physical Energy Systems, MSCPES 2022).

@inproceedings{ebbd30539813444392fbe177743d2c9d,

title = "Low-Cost Hardware Platform for Testing ML-Based Edge Power Grid Oscillation Detectors",

abstract = "This paper introduces a low-cost hardware testing platform designed to investigate the performance of a Machine Learning (ML)-based edge application developed to detect forced oscillations in power grids. The core of the ML application lies in a Convolutional Neural Network (CNN) model deployed on an ML edge device (NVIDIA Jetson TX2). The proposed platform consists of a method for real-time signal emulation using the WaveForms Software Development Kit (SDK) that defines low-voltage signals generated by Digilent's Analog Discovery Board. The output of the signal generator is read by the Jetson board using an Analog-to-Digital Converter (ADC). Our experiments compare the performance of different ADCs when performing inference with the same CNN model. Additionally, we give an overview of the communication scheme that allows experiment automation, which is particularly useful when experiment design is time-consuming and laborious.",

keywords = "Convolutional Neural Network, Data Acquisition, Experiment Automation, Forced Oscillations, Real-Time Signal Emulation",

author = "Dorado-Rojas, {Sergio A.} and Shunyao Xu and Luigi Vanfretti and Galilea Olvera and Ayachi, {M. Ilies I.} and Shehab Ahmed",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 10th Workshop on Modelling and Simulation of Cyber-Physical Energy Systems, MSCPES 2022 ; Conference date: 03-05-2022",

year = "2022",

doi = "10.1109/MSCPES55116.2022.9770146",

language = "English (US)",

series = "2022 10th Workshop on Modelling and Simulation of Cyber-Physical Energy Systems, MSCPES 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2022 10th Workshop on Modelling and Simulation of Cyber-Physical Energy Systems, MSCPES 2022",

address = "United States",

}

Dorado-Rojas, SA, Xu, S, Vanfretti, L, Olvera, G, Ayachi, MII & Ahmed, S 2022, Low-Cost Hardware Platform for Testing ML-Based Edge Power Grid Oscillation Detectors. in 2022 10th Workshop on Modelling and Simulation of Cyber-Physical Energy Systems, MSCPES 2022. 2022 10th Workshop on Modelling and Simulation of Cyber-Physical Energy Systems, MSCPES 2022, Institute of Electrical and Electronics Engineers Inc., 10th Workshop on Modelling and Simulation of Cyber-Physical Energy Systems, MSCPES 2022, Milan, Italy, 05/3/22. https://doi.org/10.1109/MSCPES55116.2022.9770146

Low-Cost Hardware Platform for Testing ML-Based Edge Power Grid Oscillation Detectors. / Dorado-Rojas, Sergio A.; Xu, Shunyao; Vanfretti, Luigi et al.
2022 10th Workshop on Modelling and Simulation of Cyber-Physical Energy Systems, MSCPES 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (2022 10th Workshop on Modelling and Simulation of Cyber-Physical Energy Systems, MSCPES 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Low-Cost Hardware Platform for Testing ML-Based Edge Power Grid Oscillation Detectors

AU - Dorado-Rojas, Sergio A.

AU - Xu, Shunyao

AU - Vanfretti, Luigi

AU - Olvera, Galilea

AU - Ayachi, M. Ilies I.

AU - Ahmed, Shehab

PY - 2022

Y1 - 2022

N2 - This paper introduces a low-cost hardware testing platform designed to investigate the performance of a Machine Learning (ML)-based edge application developed to detect forced oscillations in power grids. The core of the ML application lies in a Convolutional Neural Network (CNN) model deployed on an ML edge device (NVIDIA Jetson TX2). The proposed platform consists of a method for real-time signal emulation using the WaveForms Software Development Kit (SDK) that defines low-voltage signals generated by Digilent's Analog Discovery Board. The output of the signal generator is read by the Jetson board using an Analog-to-Digital Converter (ADC). Our experiments compare the performance of different ADCs when performing inference with the same CNN model. Additionally, we give an overview of the communication scheme that allows experiment automation, which is particularly useful when experiment design is time-consuming and laborious.

AB - This paper introduces a low-cost hardware testing platform designed to investigate the performance of a Machine Learning (ML)-based edge application developed to detect forced oscillations in power grids. The core of the ML application lies in a Convolutional Neural Network (CNN) model deployed on an ML edge device (NVIDIA Jetson TX2). The proposed platform consists of a method for real-time signal emulation using the WaveForms Software Development Kit (SDK) that defines low-voltage signals generated by Digilent's Analog Discovery Board. The output of the signal generator is read by the Jetson board using an Analog-to-Digital Converter (ADC). Our experiments compare the performance of different ADCs when performing inference with the same CNN model. Additionally, we give an overview of the communication scheme that allows experiment automation, which is particularly useful when experiment design is time-consuming and laborious.

KW - Convolutional Neural Network

KW - Data Acquisition

KW - Experiment Automation

KW - Forced Oscillations

KW - Real-Time Signal Emulation

UR - http://www.scopus.com/inward/record.url?scp=85130686023&partnerID=8YFLogxK

U2 - 10.1109/MSCPES55116.2022.9770146

DO - 10.1109/MSCPES55116.2022.9770146

M3 - Conference contribution

AN - SCOPUS:85130686023

T3 - 2022 10th Workshop on Modelling and Simulation of Cyber-Physical Energy Systems, MSCPES 2022

BT - 2022 10th Workshop on Modelling and Simulation of Cyber-Physical Energy Systems, MSCPES 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 10th Workshop on Modelling and Simulation of Cyber-Physical Energy Systems, MSCPES 2022

Y2 - 3 May 2022

ER -

Dorado-Rojas SA, Xu S, Vanfretti L, Olvera G, Ayachi MII , Ahmed S. Low-Cost Hardware Platform for Testing ML-Based Edge Power Grid Oscillation Detectors. In 2022 10th Workshop on Modelling and Simulation of Cyber-Physical Energy Systems, MSCPES 2022. Institute of Electrical and Electronics Engineers Inc. 2022. (2022 10th Workshop on Modelling and Simulation of Cyber-Physical Energy Systems, MSCPES 2022). doi: 10.1109/MSCPES55116.2022.9770146

Low-Cost Hardware Platform for Testing ML-Based Edge Power Grid Oscillation Detectors

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this