High-Frequency, Multiclass Nonintrusive Load Monitoring for Grid-Interactive Residential Buildings: Preprint

Blake Lundstrom; Govind Saraswat; Murti Salapaka

High-Frequency, Multiclass Nonintrusive Load Monitoring for Grid-Interactive Residential Buildings: Preprint

Blake Lundstrom, Govind Saraswat, Murti Salapaka

Power Systems Engineering

University of Minnesota

Research output: Contribution to conference › Paper

Abstract

Smart buildings with net-load metering and control capabilities can provide valuable flexibility to grid operators. This article develops a novel approach for high-frequency, multiclass nonintrusive load monitoring (NILM) that enables effective net-load monitoring capabilities with minimal additional equipment and cost. Relative to existing NILM work, the proposed solution operates at a faster timescale, providing accurate multiclass state predictions for each 60-Hz ac cycle without relying on event-detection techniques. The approach is validated using a test bed with residential appliances and shown to have high accuracy, good generalization properties, and sufficient response time to support building grid-interactive control at fast timescales relevant to the provision of grid frequency support services.

Original language	American English
Number of pages	8
State	Published - 2019
Event	2020 IEEE Conference on Innovative Smart Grid Technologies (IEEE ISGT) - Washington, D.C. Duration: 17 Feb 2020 → 20 Feb 2020

Conference

Conference	2020 IEEE Conference on Innovative Smart Grid Technologies (IEEE ISGT)
City	Washington, D.C.
Period	17/02/20 → 20/02/20

Bibliographical note

See NREL/CP-5D00-77279 for paper as published in IEEE proceedings

NREL Publication Number

NREL/CP-5D00-74701

Keywords

feature extraction
grid-interactive
multiclass classification
nonintrusive load monitoring (NILM)
smart buildings

Access to Document

https://www.nrel.gov/docs/fy20osti/74701.pdf

Cite this

@conference{1a752aabd1ca4bf7ab565c18d03c5323,

title = "High-Frequency, Multiclass Nonintrusive Load Monitoring for Grid-Interactive Residential Buildings: Preprint",

abstract = "Smart buildings with net-load metering and control capabilities can provide valuable flexibility to grid operators. This article develops a novel approach for high-frequency, multiclass nonintrusive load monitoring (NILM) that enables effective net-load monitoring capabilities with minimal additional equipment and cost. Relative to existing NILM work, the proposed solution operates at a faster timescale, providing accurate multiclass state predictions for each 60-Hz ac cycle without relying on event-detection techniques. The approach is validated using a test bed with residential appliances and shown to have high accuracy, good generalization properties, and sufficient response time to support building grid-interactive control at fast timescales relevant to the provision of grid frequency support services.",

keywords = "feature extraction, grid-interactive, multiclass classification, nonintrusive load monitoring (NILM), smart buildings",

author = "Blake Lundstrom and Govind Saraswat and Murti Salapaka",

note = "See NREL/CP-5D00-77279 for paper as published in IEEE proceedings; 2020 IEEE Conference on Innovative Smart Grid Technologies (IEEE ISGT) ; Conference date: 17-02-2020 Through 20-02-2020",

year = "2019",

language = "American English",

}

TY - CONF

T1 - High-Frequency, Multiclass Nonintrusive Load Monitoring for Grid-Interactive Residential Buildings: Preprint

AU - Lundstrom, Blake

AU - Saraswat, Govind

AU - Salapaka, Murti

N1 - See NREL/CP-5D00-77279 for paper as published in IEEE proceedings

PY - 2019

Y1 - 2019

N2 - Smart buildings with net-load metering and control capabilities can provide valuable flexibility to grid operators. This article develops a novel approach for high-frequency, multiclass nonintrusive load monitoring (NILM) that enables effective net-load monitoring capabilities with minimal additional equipment and cost. Relative to existing NILM work, the proposed solution operates at a faster timescale, providing accurate multiclass state predictions for each 60-Hz ac cycle without relying on event-detection techniques. The approach is validated using a test bed with residential appliances and shown to have high accuracy, good generalization properties, and sufficient response time to support building grid-interactive control at fast timescales relevant to the provision of grid frequency support services.

AB - Smart buildings with net-load metering and control capabilities can provide valuable flexibility to grid operators. This article develops a novel approach for high-frequency, multiclass nonintrusive load monitoring (NILM) that enables effective net-load monitoring capabilities with minimal additional equipment and cost. Relative to existing NILM work, the proposed solution operates at a faster timescale, providing accurate multiclass state predictions for each 60-Hz ac cycle without relying on event-detection techniques. The approach is validated using a test bed with residential appliances and shown to have high accuracy, good generalization properties, and sufficient response time to support building grid-interactive control at fast timescales relevant to the provision of grid frequency support services.

KW - feature extraction

KW - grid-interactive

KW - multiclass classification

KW - nonintrusive load monitoring (NILM)

KW - smart buildings

M3 - Paper

T2 - 2020 IEEE Conference on Innovative Smart Grid Technologies (IEEE ISGT)

Y2 - 17 February 2020 through 20 February 2020

ER -

High-Frequency, Multiclass Nonintrusive Load Monitoring for Grid-Interactive Residential Buildings: Preprint

Abstract

Conference

Bibliographical note

NREL Publication Number

Keywords

Access to Document

Fingerprint

Cite this