Adaptive segmentation and machine learning based potential DR capacity analysis

Wen Jun Tang, Yi Syuan Wu, Hong-Tzer Yang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

By shedding their electricity consumption or getting ready to be shed, the Demand Response (DR) program compensates the shortage of generation or acts as spinning reserve. Depending on how the end-users join in the program. the potential capacity of DR is, therefore, a key issue no matter to system operator or DR aggregator. The proposed method employs adaptive k-means approach to evaluate the potential consumer as candidate participants of DR. The consumption prediction models of controllable appliances are constructed by Gaussian Processes for Machine Learning (GPML). Through combining the candidates' data and prediction models, the potential capacity is then achieved. Case studies evaluate the accuracy and efficacy of the proposed method with practical low voltage advanced metering infrastructure (LVAMI) data achieved from Taiwan. The results show good efficiency and practicability of the proposed method.

Original languageEnglish
Title of host publicationICHQP 2018 - 18th International Conference on Harmonics and Quality of Power
PublisherIEEE Computer Society
Pages1-5
Number of pages5
ISBN (Electronic)9781538605172
DOIs
Publication statusPublished - 2018 Jun 8
Event18th International Conference on Harmonics and Quality of Power, ICHQP 2018 - Ljubljana, Slovenia
Duration: 2018 May 132018 May 16

Publication series

NameProceedings of International Conference on Harmonics and Quality of Power, ICHQP
Volume2018-May
ISSN (Print)1540-6008
ISSN (Electronic)2164-0610

Other

Other18th International Conference on Harmonics and Quality of Power, ICHQP 2018
CountrySlovenia
CityLjubljana
Period18-05-1318-05-16

Fingerprint

Learning systems
Advanced metering infrastructures
Electricity
Electric potential

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Signal Processing
  • Energy Engineering and Power Technology
  • Fuel Technology
  • Electrical and Electronic Engineering

Cite this

Tang, W. J., Wu, Y. S., & Yang, H-T. (2018). Adaptive segmentation and machine learning based potential DR capacity analysis. In ICHQP 2018 - 18th International Conference on Harmonics and Quality of Power (pp. 1-5). (Proceedings of International Conference on Harmonics and Quality of Power, ICHQP; Vol. 2018-May). IEEE Computer Society. https://doi.org/10.1109/ICHQP.2018.8378922
Tang, Wen Jun ; Wu, Yi Syuan ; Yang, Hong-Tzer. / Adaptive segmentation and machine learning based potential DR capacity analysis. ICHQP 2018 - 18th International Conference on Harmonics and Quality of Power. IEEE Computer Society, 2018. pp. 1-5 (Proceedings of International Conference on Harmonics and Quality of Power, ICHQP).
@inproceedings{2c1b2a0ed9ee4fd594648aa45e24488c,
title = "Adaptive segmentation and machine learning based potential DR capacity analysis",
abstract = "By shedding their electricity consumption or getting ready to be shed, the Demand Response (DR) program compensates the shortage of generation or acts as spinning reserve. Depending on how the end-users join in the program. the potential capacity of DR is, therefore, a key issue no matter to system operator or DR aggregator. The proposed method employs adaptive k-means approach to evaluate the potential consumer as candidate participants of DR. The consumption prediction models of controllable appliances are constructed by Gaussian Processes for Machine Learning (GPML). Through combining the candidates' data and prediction models, the potential capacity is then achieved. Case studies evaluate the accuracy and efficacy of the proposed method with practical low voltage advanced metering infrastructure (LVAMI) data achieved from Taiwan. The results show good efficiency and practicability of the proposed method.",
author = "Tang, {Wen Jun} and Wu, {Yi Syuan} and Hong-Tzer Yang",
year = "2018",
month = "6",
day = "8",
doi = "10.1109/ICHQP.2018.8378922",
language = "English",
series = "Proceedings of International Conference on Harmonics and Quality of Power, ICHQP",
publisher = "IEEE Computer Society",
pages = "1--5",
booktitle = "ICHQP 2018 - 18th International Conference on Harmonics and Quality of Power",
address = "United States",

}

Tang, WJ, Wu, YS & Yang, H-T 2018, Adaptive segmentation and machine learning based potential DR capacity analysis. in ICHQP 2018 - 18th International Conference on Harmonics and Quality of Power. Proceedings of International Conference on Harmonics and Quality of Power, ICHQP, vol. 2018-May, IEEE Computer Society, pp. 1-5, 18th International Conference on Harmonics and Quality of Power, ICHQP 2018, Ljubljana, Slovenia, 18-05-13. https://doi.org/10.1109/ICHQP.2018.8378922

Adaptive segmentation and machine learning based potential DR capacity analysis. / Tang, Wen Jun; Wu, Yi Syuan; Yang, Hong-Tzer.

ICHQP 2018 - 18th International Conference on Harmonics and Quality of Power. IEEE Computer Society, 2018. p. 1-5 (Proceedings of International Conference on Harmonics and Quality of Power, ICHQP; Vol. 2018-May).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Adaptive segmentation and machine learning based potential DR capacity analysis

AU - Tang, Wen Jun

AU - Wu, Yi Syuan

AU - Yang, Hong-Tzer

PY - 2018/6/8

Y1 - 2018/6/8

N2 - By shedding their electricity consumption or getting ready to be shed, the Demand Response (DR) program compensates the shortage of generation or acts as spinning reserve. Depending on how the end-users join in the program. the potential capacity of DR is, therefore, a key issue no matter to system operator or DR aggregator. The proposed method employs adaptive k-means approach to evaluate the potential consumer as candidate participants of DR. The consumption prediction models of controllable appliances are constructed by Gaussian Processes for Machine Learning (GPML). Through combining the candidates' data and prediction models, the potential capacity is then achieved. Case studies evaluate the accuracy and efficacy of the proposed method with practical low voltage advanced metering infrastructure (LVAMI) data achieved from Taiwan. The results show good efficiency and practicability of the proposed method.

AB - By shedding their electricity consumption or getting ready to be shed, the Demand Response (DR) program compensates the shortage of generation or acts as spinning reserve. Depending on how the end-users join in the program. the potential capacity of DR is, therefore, a key issue no matter to system operator or DR aggregator. The proposed method employs adaptive k-means approach to evaluate the potential consumer as candidate participants of DR. The consumption prediction models of controllable appliances are constructed by Gaussian Processes for Machine Learning (GPML). Through combining the candidates' data and prediction models, the potential capacity is then achieved. Case studies evaluate the accuracy and efficacy of the proposed method with practical low voltage advanced metering infrastructure (LVAMI) data achieved from Taiwan. The results show good efficiency and practicability of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=85049259864&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049259864&partnerID=8YFLogxK

U2 - 10.1109/ICHQP.2018.8378922

DO - 10.1109/ICHQP.2018.8378922

M3 - Conference contribution

T3 - Proceedings of International Conference on Harmonics and Quality of Power, ICHQP

SP - 1

EP - 5

BT - ICHQP 2018 - 18th International Conference on Harmonics and Quality of Power

PB - IEEE Computer Society

ER -

Tang WJ, Wu YS, Yang H-T. Adaptive segmentation and machine learning based potential DR capacity analysis. In ICHQP 2018 - 18th International Conference on Harmonics and Quality of Power. IEEE Computer Society. 2018. p. 1-5. (Proceedings of International Conference on Harmonics and Quality of Power, ICHQP). https://doi.org/10.1109/ICHQP.2018.8378922