University of Hertfordshire

From the same journal

By the same authors

Standard

Statistical and Electrical Features Evaluation for Electrical Appliances Energy Disaggregation. / Schirmer, Pascal; Mporas, Iosif.

In: Sustainability, Vol. 11, No. 11, 3222, 11.06.2019.

Research output: Contribution to journalArticle

Harvard

APA

Vancouver

Author

Bibtex

@article{cc786075f8484c8e846c24d01cbefd6d,
title = "Statistical and Electrical Features Evaluation for Electrical Appliances Energy Disaggregation",
abstract = "In this paper we evaluate several well-known and widely used machine learning algorithms for regression in the energy disaggregation task. Specifically, the Non-Intrusive Load Monitoring approach was considered and the K-Nearest-Neighbours, Support Vector Machines, Deep Neural Networks and Random Forest algorithms were evaluated across five datasets using seven different sets of statistical and electrical features. The experimental results demonstrated the importance of selecting both appropriate features and regression algorithms. Analysis on device level showed that linear devices can be disaggregated using statistical features, while for non-linear devices the use of electrical features significantly improves the disaggregation accuracy, as non-linear appliances have non-sinusoidal current draw and thus cannot be well parametrized only by their active power consumption. The best performance in terms of energy disaggregation accuracy was achieved by the Random Forest regression algorithm.",
keywords = "Energy disaggregation, Feature selection, Non-intrusive load monitoring (NILM)",
author = "Pascal Schirmer and Iosif Mporas",
year = "2019",
month = jun,
day = "11",
doi = "10.3390/su11113222",
language = "English",
volume = "11",
journal = "Sustainability",
issn = "2071-1050",
publisher = "MDPI AG",
number = "11",

}

RIS

TY - JOUR

T1 - Statistical and Electrical Features Evaluation for Electrical Appliances Energy Disaggregation

AU - Schirmer, Pascal

AU - Mporas, Iosif

PY - 2019/6/11

Y1 - 2019/6/11

N2 - In this paper we evaluate several well-known and widely used machine learning algorithms for regression in the energy disaggregation task. Specifically, the Non-Intrusive Load Monitoring approach was considered and the K-Nearest-Neighbours, Support Vector Machines, Deep Neural Networks and Random Forest algorithms were evaluated across five datasets using seven different sets of statistical and electrical features. The experimental results demonstrated the importance of selecting both appropriate features and regression algorithms. Analysis on device level showed that linear devices can be disaggregated using statistical features, while for non-linear devices the use of electrical features significantly improves the disaggregation accuracy, as non-linear appliances have non-sinusoidal current draw and thus cannot be well parametrized only by their active power consumption. The best performance in terms of energy disaggregation accuracy was achieved by the Random Forest regression algorithm.

AB - In this paper we evaluate several well-known and widely used machine learning algorithms for regression in the energy disaggregation task. Specifically, the Non-Intrusive Load Monitoring approach was considered and the K-Nearest-Neighbours, Support Vector Machines, Deep Neural Networks and Random Forest algorithms were evaluated across five datasets using seven different sets of statistical and electrical features. The experimental results demonstrated the importance of selecting both appropriate features and regression algorithms. Analysis on device level showed that linear devices can be disaggregated using statistical features, while for non-linear devices the use of electrical features significantly improves the disaggregation accuracy, as non-linear appliances have non-sinusoidal current draw and thus cannot be well parametrized only by their active power consumption. The best performance in terms of energy disaggregation accuracy was achieved by the Random Forest regression algorithm.

KW - Energy disaggregation

KW - Feature selection

KW - Non-intrusive load monitoring (NILM)

UR - http://www.scopus.com/inward/record.url?scp=85067233399&partnerID=8YFLogxK

U2 - 10.3390/su11113222

DO - 10.3390/su11113222

M3 - Article

VL - 11

JO - Sustainability

JF - Sustainability

SN - 2071-1050

IS - 11

M1 - 3222

ER -