Evaluation of Regression Algorithms and Features on the Energy Disaggregation Task

Pascal A. Schirmer; Iosif Mporas; Michael Paraskevas

doi:10.1109/IISA.2019.8900695

Evaluation of Regression Algorithms and Features on the Energy Disaggregation Task

Pascal A. Schirmer, Iosif Mporas, Michael Paraskevas

School of Physics, Engineering & Computer Science

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

3 Citations (Scopus)

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. The best performance in terms of energy disaggregation accuracy was achieved by the Random Forest regression algorithm.

Original language	English
Title of host publication	10th International Conference on Information, Intelligence, Systems and Applications, IISA 2019
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
ISBN (Electronic)	9781728149592
DOIs	https://doi.org/10.1109/IISA.2019.8900695
Publication status	Published - Jul 2019
Event	10th International Conference on Information, Intelligence, Systems and Applications, IISA 2019 - Patras, Greece Duration: 15 Jul 2019 → 17 Jul 2019

Publication series

Name	10th International Conference on Information, Intelligence, Systems and Applications, IISA 2019

Conference

Conference	10th International Conference on Information, Intelligence, Systems and Applications, IISA 2019
Country/Territory	Greece
City	Patras
Period	15/07/19 → 17/07/19

Keywords

Energy disaggregation
Feature selection
Non-Intrusive Load Monitoring (NILM)

Access to Document

10.1109/IISA.2019.8900695

Cite this

Schirmer, P. A., Mporas, I., & Paraskevas, M. (2019). Evaluation of Regression Algorithms and Features on the Energy Disaggregation Task. In 10th International Conference on Information, Intelligence, Systems and Applications, IISA 2019 [8900695] (10th International Conference on Information, Intelligence, Systems and Applications, IISA 2019). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/IISA.2019.8900695

Schirmer, Pascal A. ; Mporas, Iosif ; Paraskevas, Michael. / Evaluation of Regression Algorithms and Features on the Energy Disaggregation Task. 10th International Conference on Information, Intelligence, Systems and Applications, IISA 2019. Institute of Electrical and Electronics Engineers (IEEE), 2019. (10th International Conference on Information, Intelligence, Systems and Applications, IISA 2019).

@inproceedings{252abb6f83c8458f9e85002ad3784d75,

title = "Evaluation of Regression Algorithms and Features on the Energy Disaggregation Task",

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. 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 = "Schirmer, {Pascal A.} and Iosif Mporas and Michael Paraskevas",

year = "2019",

month = jul,

doi = "10.1109/IISA.2019.8900695",

language = "English",

series = "10th International Conference on Information, Intelligence, Systems and Applications, IISA 2019",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

booktitle = "10th International Conference on Information, Intelligence, Systems and Applications, IISA 2019",

note = "10th International Conference on Information, Intelligence, Systems and Applications, IISA 2019 ; Conference date: 15-07-2019 Through 17-07-2019",

}

Schirmer, PA, Mporas, I & Paraskevas, M 2019, Evaluation of Regression Algorithms and Features on the Energy Disaggregation Task. in 10th International Conference on Information, Intelligence, Systems and Applications, IISA 2019., 8900695, 10th International Conference on Information, Intelligence, Systems and Applications, IISA 2019, Institute of Electrical and Electronics Engineers (IEEE), 10th International Conference on Information, Intelligence, Systems and Applications, IISA 2019, Patras, Greece, 15/07/19. https://doi.org/10.1109/IISA.2019.8900695

Evaluation of Regression Algorithms and Features on the Energy Disaggregation Task. / Schirmer, Pascal A.; Mporas, Iosif; Paraskevas, Michael.
10th International Conference on Information, Intelligence, Systems and Applications, IISA 2019. Institute of Electrical and Electronics Engineers (IEEE), 2019. 8900695 (10th International Conference on Information, Intelligence, Systems and Applications, IISA 2019).

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

TY - GEN

T1 - Evaluation of Regression Algorithms and Features on the Energy Disaggregation Task

AU - Schirmer, Pascal A.

AU - Mporas, Iosif

AU - Paraskevas, Michael

PY - 2019/7

Y1 - 2019/7

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. 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. 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=85075853138&partnerID=8YFLogxK

U2 - 10.1109/IISA.2019.8900695

DO - 10.1109/IISA.2019.8900695

M3 - Conference contribution

T3 - 10th International Conference on Information, Intelligence, Systems and Applications, IISA 2019

BT - 10th International Conference on Information, Intelligence, Systems and Applications, IISA 2019

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 10th International Conference on Information, Intelligence, Systems and Applications, IISA 2019

Y2 - 15 July 2019 through 17 July 2019

ER -

Schirmer PA, Mporas I, Paraskevas M. Evaluation of Regression Algorithms and Features on the Energy Disaggregation Task. In 10th International Conference on Information, Intelligence, Systems and Applications, IISA 2019. Institute of Electrical and Electronics Engineers (IEEE). 2019. 8900695. (10th International Conference on Information, Intelligence, Systems and Applications, IISA 2019). doi: 10.1109/IISA.2019.8900695

Evaluation of Regression Algorithms and Features on the Energy Disaggregation Task

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this