An in-depth study of forecasting household electricity demand using realistic datasets

Chien Yu Kuo, Ming Feng Lee, Chia Lin Fu, Yao-Hua Ho, Ling-Jyh Chen

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

4 Citations (Scopus)

Abstract

Data analysis and accurate forecasts of electricity demand are crucial to help both suppliers and consumers understand their detailed electricity footprints and improve their awareness about their impacts to the ecosystem. Several studies of the subject have been conducted in recent years, but they are either comprehension-oriented without practical merits; or they are forecast-oriented and do not consider per-consumer cases. To address this gap, in this paper, we conduct data analysis and evaluate the forecasting of household electricity demand using three realistic datasets of geospatial and lifestyle diversity. We investigate the correlations between household electricity demand and different external factors, and perform cluster analysis on the datasets using an exhaustive set of parameter settings. To evaluate the accuracy of electricity demand forecasts in different datasets, we use the support vector regression method. The results demonstrate that the medium mean absolute percentage error (MAPE) can be reduced to 15.6% for household electricity demand forecasts when proper configurations are used.

Original languageEnglish
Title of host publicatione-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems
PublisherAssociation for Computing Machinery
Pages145-155
Number of pages11
ISBN (Print)9781450328197
DOIs
Publication statusPublished - 2014 Jan 1
Event5th ACM International Conference on Future Energy Systems, e-Energy 2014 - Cambridge, United Kingdom
Duration: 2014 Jun 112014 Jun 13

Publication series

Namee-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems

Other

Other5th ACM International Conference on Future Energy Systems, e-Energy 2014
CountryUnited Kingdom
CityCambridge
Period14/6/1114/6/13

Fingerprint

Electricity
Cluster analysis
Ecosystems

Keywords

  • data analysis
  • electricity demand forecast
  • household electricity demand

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Fuel Technology

Cite this

Kuo, C. Y., Lee, M. F., Fu, C. L., Ho, Y-H., & Chen, L-J. (2014). An in-depth study of forecasting household electricity demand using realistic datasets. In e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems (pp. 145-155). (e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems). Association for Computing Machinery. https://doi.org/10.1145/2602044.2602055

An in-depth study of forecasting household electricity demand using realistic datasets. / Kuo, Chien Yu; Lee, Ming Feng; Fu, Chia Lin; Ho, Yao-Hua; Chen, Ling-Jyh.

e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems. Association for Computing Machinery, 2014. p. 145-155 (e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems).

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

Kuo, CY, Lee, MF, Fu, CL, Ho, Y-H & Chen, L-J 2014, An in-depth study of forecasting household electricity demand using realistic datasets. in e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems. e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems, Association for Computing Machinery, pp. 145-155, 5th ACM International Conference on Future Energy Systems, e-Energy 2014, Cambridge, United Kingdom, 14/6/11. https://doi.org/10.1145/2602044.2602055
Kuo CY, Lee MF, Fu CL, Ho Y-H, Chen L-J. An in-depth study of forecasting household electricity demand using realistic datasets. In e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems. Association for Computing Machinery. 2014. p. 145-155. (e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems). https://doi.org/10.1145/2602044.2602055
Kuo, Chien Yu ; Lee, Ming Feng ; Fu, Chia Lin ; Ho, Yao-Hua ; Chen, Ling-Jyh. / An in-depth study of forecasting household electricity demand using realistic datasets. e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems. Association for Computing Machinery, 2014. pp. 145-155 (e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems).
@inproceedings{c3156032eed14757a0f71873dbf75df6,
title = "An in-depth study of forecasting household electricity demand using realistic datasets",
abstract = "Data analysis and accurate forecasts of electricity demand are crucial to help both suppliers and consumers understand their detailed electricity footprints and improve their awareness about their impacts to the ecosystem. Several studies of the subject have been conducted in recent years, but they are either comprehension-oriented without practical merits; or they are forecast-oriented and do not consider per-consumer cases. To address this gap, in this paper, we conduct data analysis and evaluate the forecasting of household electricity demand using three realistic datasets of geospatial and lifestyle diversity. We investigate the correlations between household electricity demand and different external factors, and perform cluster analysis on the datasets using an exhaustive set of parameter settings. To evaluate the accuracy of electricity demand forecasts in different datasets, we use the support vector regression method. The results demonstrate that the medium mean absolute percentage error (MAPE) can be reduced to 15.6{\%} for household electricity demand forecasts when proper configurations are used.",
keywords = "data analysis, electricity demand forecast, household electricity demand",
author = "Kuo, {Chien Yu} and Lee, {Ming Feng} and Fu, {Chia Lin} and Yao-Hua Ho and Ling-Jyh Chen",
year = "2014",
month = "1",
day = "1",
doi = "10.1145/2602044.2602055",
language = "English",
isbn = "9781450328197",
series = "e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems",
publisher = "Association for Computing Machinery",
pages = "145--155",
booktitle = "e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems",

}

TY - GEN

T1 - An in-depth study of forecasting household electricity demand using realistic datasets

AU - Kuo, Chien Yu

AU - Lee, Ming Feng

AU - Fu, Chia Lin

AU - Ho, Yao-Hua

AU - Chen, Ling-Jyh

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Data analysis and accurate forecasts of electricity demand are crucial to help both suppliers and consumers understand their detailed electricity footprints and improve their awareness about their impacts to the ecosystem. Several studies of the subject have been conducted in recent years, but they are either comprehension-oriented without practical merits; or they are forecast-oriented and do not consider per-consumer cases. To address this gap, in this paper, we conduct data analysis and evaluate the forecasting of household electricity demand using three realistic datasets of geospatial and lifestyle diversity. We investigate the correlations between household electricity demand and different external factors, and perform cluster analysis on the datasets using an exhaustive set of parameter settings. To evaluate the accuracy of electricity demand forecasts in different datasets, we use the support vector regression method. The results demonstrate that the medium mean absolute percentage error (MAPE) can be reduced to 15.6% for household electricity demand forecasts when proper configurations are used.

AB - Data analysis and accurate forecasts of electricity demand are crucial to help both suppliers and consumers understand their detailed electricity footprints and improve their awareness about their impacts to the ecosystem. Several studies of the subject have been conducted in recent years, but they are either comprehension-oriented without practical merits; or they are forecast-oriented and do not consider per-consumer cases. To address this gap, in this paper, we conduct data analysis and evaluate the forecasting of household electricity demand using three realistic datasets of geospatial and lifestyle diversity. We investigate the correlations between household electricity demand and different external factors, and perform cluster analysis on the datasets using an exhaustive set of parameter settings. To evaluate the accuracy of electricity demand forecasts in different datasets, we use the support vector regression method. The results demonstrate that the medium mean absolute percentage error (MAPE) can be reduced to 15.6% for household electricity demand forecasts when proper configurations are used.

KW - data analysis

KW - electricity demand forecast

KW - household electricity demand

UR - http://www.scopus.com/inward/record.url?scp=84907013139&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84907013139&partnerID=8YFLogxK

U2 - 10.1145/2602044.2602055

DO - 10.1145/2602044.2602055

M3 - Conference contribution

AN - SCOPUS:84907013139

SN - 9781450328197

T3 - e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems

SP - 145

EP - 155

BT - e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems

PB - Association for Computing Machinery

ER -