Modified Cross-Entropy Method for Classification of Events in NILM Systems  A New Hybrid State Estimation Considering

Ram Machlev; Yoash Levron; Yuval Beck

doi:10.1109/TSG.2018.2871620

Modified Cross-Entropy Method for Classification of Events in NILM Systems A New Hybrid State Estimation Considering

Ram Machlev, Yoash Levron, Yuval Beck

Electrical and Computer Engineering

Research output: Contribution to journal › Article › peer-review

Abstract

Non-intrusive load monitoring is an algorithm or process that disaggregates the total power in a facility to identify consumption of individual appliances. In this paper, a new algorithm is proposed to classify events of appliance states based on modification of the cross-entropy (CE) method. The main contribution is a formulation and solution of the problem with the CE method as a constrained optimization problem. This new technique is called the modified CE method. The proposed algorithm is simple, as it operates in real time, using low rate sampling of the active power. In addition, there is no need to train the system or to use complex hardware. The algorithm is tested using the REDD and AMPds datasets and the results are compared to several state-of-the-art techniques.

Original language	English
Pages (from-to)	4962-4973
Number of pages	12
Journal	IEEE Transactions on Smart Grid
Volume	10
Issue number	5
DOIs	https://doi.org/10.1109/TSG.2018.2871620
State	Published - 2021

Keywords

Cross-Entropy Method (CE)
Smart Grid.
load-disaggregation
non-intrusive load monitoring (NILM)

ASJC Scopus subject areas

General Computer Science

UN SDGs

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

Access to Document

10.1109/TSG.2018.2871620

Cite this

@article{d1aa46faedc243ab885904e691c5579d,

title = "Modified Cross-Entropy Method for Classification of Events in NILM Systems A New Hybrid State Estimation Considering ",

abstract = "Non-intrusive load monitoring is an algorithm or process that disaggregates the total power in a facility to identify consumption of individual appliances. In this paper, a new algorithm is proposed to classify events of appliance states based on modification of the cross-entropy (CE) method. The main contribution is a formulation and solution of the problem with the CE method as a constrained optimization problem. This new technique is called the modified CE method. The proposed algorithm is simple, as it operates in real time, using low rate sampling of the active power. In addition, there is no need to train the system or to use complex hardware. The algorithm is tested using the REDD and AMPds datasets and the results are compared to several state-of-the-art techniques.",

keywords = "Cross-Entropy Method (CE), Smart Grid., load-disaggregation, non-intrusive load monitoring (NILM)",

author = "Ram Machlev and Yoash Levron and Yuval Beck",

note = "Publisher Copyright: IEEE",

year = "2021",

doi = "10.1109/TSG.2018.2871620",

language = "אנגלית",

volume = "10",

pages = "4962--4973",

number = "5",

}

TY - JOUR

T1 - Modified Cross-Entropy Method for Classification of Events in NILM Systems A New Hybrid State Estimation Considering

AU - Machlev, Ram

AU - Levron, Yoash

AU - Beck, Yuval

N1 - Publisher Copyright: IEEE

PY - 2021

Y1 - 2021

N2 - Non-intrusive load monitoring is an algorithm or process that disaggregates the total power in a facility to identify consumption of individual appliances. In this paper, a new algorithm is proposed to classify events of appliance states based on modification of the cross-entropy (CE) method. The main contribution is a formulation and solution of the problem with the CE method as a constrained optimization problem. This new technique is called the modified CE method. The proposed algorithm is simple, as it operates in real time, using low rate sampling of the active power. In addition, there is no need to train the system or to use complex hardware. The algorithm is tested using the REDD and AMPds datasets and the results are compared to several state-of-the-art techniques.

AB - Non-intrusive load monitoring is an algorithm or process that disaggregates the total power in a facility to identify consumption of individual appliances. In this paper, a new algorithm is proposed to classify events of appliance states based on modification of the cross-entropy (CE) method. The main contribution is a formulation and solution of the problem with the CE method as a constrained optimization problem. This new technique is called the modified CE method. The proposed algorithm is simple, as it operates in real time, using low rate sampling of the active power. In addition, there is no need to train the system or to use complex hardware. The algorithm is tested using the REDD and AMPds datasets and the results are compared to several state-of-the-art techniques.

KW - Cross-Entropy Method (CE)

KW - Smart Grid.

KW - load-disaggregation

KW - non-intrusive load monitoring (NILM)

UR - http://www.scopus.com/inward/record.url?scp=85053622280&partnerID=8YFLogxK

U2 - 10.1109/TSG.2018.2871620

DO - 10.1109/TSG.2018.2871620

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

AN - SCOPUS:85053622280

SN - 1949-3053

VL - 10

SP - 4962

EP - 4973

JO - IEEE Transactions on Smart Grid

JF - IEEE Transactions on Smart Grid

IS - 5

ER -