Scalable Hybrid Classification-Regression Solution for High-Frequency Nonintrusive Load Monitoring

Govind Saraswat; Blake Lundstrom; Murti V. Salapaka

doi:10.1109/ISGT51731.2023.10066447

Scalable Hybrid Classification-Regression Solution for High-Frequency Nonintrusive Load Monitoring

Govind Saraswat, Blake Lundstrom, Murti V. Salapaka

Electrical and Computer Engineering

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

Abstract

Residential buildings with the ability to monitor and control their net-load (sum of load and generation) can provide valuable flexibility to power grid operators. We present a novel multiclass nonintrusive load monitoring (NILM) approach that enables effective net-load monitoring capabilities at high-frequency with minimal additional equipment and cost. The proposed machine learning based solution provides accurate multiclass state predictions while operating at a faster timescale (able to provide a prediction for each 60- Hz ac cycle used in US power grid) without relying on event-detection techniques. We also introduce an innovative hybrid classification-regression method that allows for the prediction of not only load on/off states but also individual load operating power levels. A test bed with eight residential appliances is used for validating the NILM approach. Results show that the overall method has high accuracy, good scaling and generalization properties.

Original language	English (US)
Title of host publication	2023 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665453554
DOIs	https://doi.org/10.1109/ISGT51731.2023.10066447
State	Published - 2023
Event	2023 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2023 - Washington, United States Duration: Jan 16 2023 → Jan 19 2023

Publication series

Name	2023 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2023

Conference

Conference	2023 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2023
Country/Territory	United States
City	Washington
Period	1/16/23 → 1/19/23

Bibliographical note

Funding Information:
1National Renewable Energy Laboratory,Golden, CO, USA; 2Enphase, Austin, TX, USA; 3University of Minnesota, Minneapolis, MN, USA The authors acknowledge the Advanced Research Projects Agency-Energy (ARPA-E) for supporting this research through the project titled “Rapidly Viable Sustained Grid” via grant no. DE-AR0001016. This work was authored in part by the National Renewable Energy Laboratory, managed and operated by Alliance for Sustainable Energy, LLC, for the U.S. Department of Energy (DOE) under Contract No. DE-AC36-08GO28308. The views expressed in the article do not necessarily represent the views of the DOE or the U.S. Government. The U.S. Government retains and the publisher, by accepting the article for publication, acknowledges that the U.S. Government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this work, or allow others to do so, for U.S. Government purposes

Publisher Copyright:
© 2023 IEEE.

Keywords

Nonintrusive load monitoring (NILM)
feature extraction
grid-interactive
multiclass classification
power prediction
regression
smart buildings
smart grid

UN SDGs

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

Publisher link

10.1109/ISGT51731.2023.10066447

Find It

Find It at U of M Libraries

Cite this

Saraswat, G., Lundstrom, B., & Salapaka, M. V. (2023). Scalable Hybrid Classification-Regression Solution for High-Frequency Nonintrusive Load Monitoring. In 2023 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2023 (2023 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISGT51731.2023.10066447

Scalable Hybrid Classification-Regression Solution for High-Frequency Nonintrusive Load Monitoring. / Saraswat, Govind; Lundstrom, Blake; Salapaka, Murti V.
2023 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2023).

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

Saraswat, G, Lundstrom, B & Salapaka, MV 2023, Scalable Hybrid Classification-Regression Solution for High-Frequency Nonintrusive Load Monitoring. in 2023 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2023. 2023 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2023, Institute of Electrical and Electronics Engineers Inc., 2023 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2023, Washington, United States, 1/16/23. https://doi.org/10.1109/ISGT51731.2023.10066447

Saraswat G, Lundstrom B, Salapaka MV. Scalable Hybrid Classification-Regression Solution for High-Frequency Nonintrusive Load Monitoring. In 2023 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2023. Institute of Electrical and Electronics Engineers Inc. 2023. (2023 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2023). doi: 10.1109/ISGT51731.2023.10066447

Saraswat, Govind ; Lundstrom, Blake ; Salapaka, Murti V. / Scalable Hybrid Classification-Regression Solution for High-Frequency Nonintrusive Load Monitoring. 2023 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2023).

@inproceedings{8d92e93f578e421b9e93387e4e7a203c,

title = "Scalable Hybrid Classification-Regression Solution for High-Frequency Nonintrusive Load Monitoring",

abstract = "Residential buildings with the ability to monitor and control their net-load (sum of load and generation) can provide valuable flexibility to power grid operators. We present a novel multiclass nonintrusive load monitoring (NILM) approach that enables effective net-load monitoring capabilities at high-frequency with minimal additional equipment and cost. The proposed machine learning based solution provides accurate multiclass state predictions while operating at a faster timescale (able to provide a prediction for each 60- Hz ac cycle used in US power grid) without relying on event-detection techniques. We also introduce an innovative hybrid classification-regression method that allows for the prediction of not only load on/off states but also individual load operating power levels. A test bed with eight residential appliances is used for validating the NILM approach. Results show that the overall method has high accuracy, good scaling and generalization properties.",

keywords = "Nonintrusive load monitoring (NILM), feature extraction, grid-interactive, multiclass classification, power prediction, regression, smart buildings, smart grid",

author = "Govind Saraswat and Blake Lundstrom and Salapaka, {Murti V.}",

note = "Funding Information: 1National Renewable Energy Laboratory,Golden, CO, USA; 2Enphase, Austin, TX, USA; 3University of Minnesota, Minneapolis, MN, USA The authors acknowledge the Advanced Research Projects Agency-Energy (ARPA-E) for supporting this research through the project titled “Rapidly Viable Sustained Grid” via grant no. DE-AR0001016. This work was authored in part by the National Renewable Energy Laboratory, managed and operated by Alliance for Sustainable Energy, LLC, for the U.S. Department of Energy (DOE) under Contract No. DE-AC36-08GO28308. The views expressed in the article do not necessarily represent the views of the DOE or the U.S. Government. The U.S. Government retains and the publisher, by accepting the article for publication, acknowledges that the U.S. Government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this work, or allow others to do so, for U.S. Government purposes Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2023 ; Conference date: 16-01-2023 Through 19-01-2023",

year = "2023",

doi = "10.1109/ISGT51731.2023.10066447",

language = "English (US)",

series = "2023 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2023",

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

booktitle = "2023 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2023",

}

TY - GEN

T1 - Scalable Hybrid Classification-Regression Solution for High-Frequency Nonintrusive Load Monitoring

AU - Saraswat, Govind

AU - Lundstrom, Blake

AU - Salapaka, Murti V.

N1 - Funding Information: 1National Renewable Energy Laboratory,Golden, CO, USA; 2Enphase, Austin, TX, USA; 3University of Minnesota, Minneapolis, MN, USA The authors acknowledge the Advanced Research Projects Agency-Energy (ARPA-E) for supporting this research through the project titled “Rapidly Viable Sustained Grid” via grant no. DE-AR0001016. This work was authored in part by the National Renewable Energy Laboratory, managed and operated by Alliance for Sustainable Energy, LLC, for the U.S. Department of Energy (DOE) under Contract No. DE-AC36-08GO28308. The views expressed in the article do not necessarily represent the views of the DOE or the U.S. Government. The U.S. Government retains and the publisher, by accepting the article for publication, acknowledges that the U.S. Government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this work, or allow others to do so, for U.S. Government purposes Publisher Copyright: © 2023 IEEE.

PY - 2023

Y1 - 2023

N2 - Residential buildings with the ability to monitor and control their net-load (sum of load and generation) can provide valuable flexibility to power grid operators. We present a novel multiclass nonintrusive load monitoring (NILM) approach that enables effective net-load monitoring capabilities at high-frequency with minimal additional equipment and cost. The proposed machine learning based solution provides accurate multiclass state predictions while operating at a faster timescale (able to provide a prediction for each 60- Hz ac cycle used in US power grid) without relying on event-detection techniques. We also introduce an innovative hybrid classification-regression method that allows for the prediction of not only load on/off states but also individual load operating power levels. A test bed with eight residential appliances is used for validating the NILM approach. Results show that the overall method has high accuracy, good scaling and generalization properties.

AB - Residential buildings with the ability to monitor and control their net-load (sum of load and generation) can provide valuable flexibility to power grid operators. We present a novel multiclass nonintrusive load monitoring (NILM) approach that enables effective net-load monitoring capabilities at high-frequency with minimal additional equipment and cost. The proposed machine learning based solution provides accurate multiclass state predictions while operating at a faster timescale (able to provide a prediction for each 60- Hz ac cycle used in US power grid) without relying on event-detection techniques. We also introduce an innovative hybrid classification-regression method that allows for the prediction of not only load on/off states but also individual load operating power levels. A test bed with eight residential appliances is used for validating the NILM approach. Results show that the overall method has high accuracy, good scaling and generalization properties.

KW - Nonintrusive load monitoring (NILM)

KW - feature extraction

KW - grid-interactive

KW - multiclass classification

KW - power prediction

KW - regression

KW - smart buildings

KW - smart grid

UR - http://www.scopus.com/inward/record.url?scp=85151515339&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85151515339&partnerID=8YFLogxK

U2 - 10.1109/ISGT51731.2023.10066447

DO - 10.1109/ISGT51731.2023.10066447

M3 - Conference contribution

AN - SCOPUS:85151515339

T3 - 2023 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2023

BT - 2023 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2023

Y2 - 16 January 2023 through 19 January 2023

ER -

Scalable Hybrid Classification-Regression Solution for High-Frequency Nonintrusive Load Monitoring

Abstract

Publication series

Conference

Bibliographical note

Keywords

UN SDGs

Publisher link

Find It

Other files and links

Fingerprint

Cite this