Forecasting Uncertainty in Electricity Smart Meter Data by Boosting Additive Quantile Regression

Handle URI:
http://hdl.handle.net/10754/622549
Title:
Forecasting Uncertainty in Electricity Smart Meter Data by Boosting Additive Quantile Regression
Authors:
Taieb, Souhaib Ben; Huser, Raphaël ( 0000-0002-1228-2071 ) ; Hyndman, Rob J.; Genton, Marc G. ( 0000-0001-6467-2998 )
Abstract:
Smart electricity meters are currently deployed in millions of households to collect detailed individual electricity consumption data. Compared with traditional electricity data based on aggregated consumption, smart meter data are much more volatile and less predictable. There is a need within the energy industry for probabilistic forecasts of household electricity consumption to quantify the uncertainty of future electricity demand in order to undertake appropriate planning of generation and distribution. We propose to estimate an additive quantile regression model for a set of quantiles of the future distribution using a boosting procedure. By doing so, we can benefit from flexible and interpretable models, which include an automatic variable selection. We compare our approach with three benchmark methods on both aggregated and disaggregated scales using a smart meter data set collected from 3639 households in Ireland at 30-min intervals over a period of 1.5 years. The empirical results demonstrate that our approach based on quantile regression provides better forecast accuracy for disaggregated demand, while the traditional approach based on a normality assumption (possibly after an appropriate Box-Cox transformation) is a better approximation for aggregated demand. These results are particularly useful since more energy data will become available at the disaggregated level in the future.
KAUST Department:
King Abdullah University of Science and Technology, Thuwal, 23955-6900, Saudi Arabia
Citation:
Ben Taieb S, Huser R, Hyndman RJ, Genton MG (2016) Forecasting Uncertainty in Electricity Smart Meter Data by Boosting Additive Quantile Regression. IEEE Transactions on Smart Grid 7: 2448–2455. Available: http://dx.doi.org/10.1109/TSG.2016.2527820.
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
Journal:
IEEE Transactions on Smart Grid
Issue Date:
2-Mar-2016
DOI:
10.1109/TSG.2016.2527820
Type:
Article
ISSN:
1949-3053; 1949-3061
Appears in Collections:
Articles

Full metadata record

DC FieldValue Language
dc.contributor.authorTaieb, Souhaib Benen
dc.contributor.authorHuser, Raphaëlen
dc.contributor.authorHyndman, Rob J.en
dc.contributor.authorGenton, Marc G.en
dc.date.accessioned2017-01-02T09:55:29Z-
dc.date.available2017-01-02T09:55:29Z-
dc.date.issued2016-03-02en
dc.identifier.citationBen Taieb S, Huser R, Hyndman RJ, Genton MG (2016) Forecasting Uncertainty in Electricity Smart Meter Data by Boosting Additive Quantile Regression. IEEE Transactions on Smart Grid 7: 2448–2455. Available: http://dx.doi.org/10.1109/TSG.2016.2527820.en
dc.identifier.issn1949-3053en
dc.identifier.issn1949-3061en
dc.identifier.doi10.1109/TSG.2016.2527820en
dc.identifier.urihttp://hdl.handle.net/10754/622549-
dc.description.abstractSmart electricity meters are currently deployed in millions of households to collect detailed individual electricity consumption data. Compared with traditional electricity data based on aggregated consumption, smart meter data are much more volatile and less predictable. There is a need within the energy industry for probabilistic forecasts of household electricity consumption to quantify the uncertainty of future electricity demand in order to undertake appropriate planning of generation and distribution. We propose to estimate an additive quantile regression model for a set of quantiles of the future distribution using a boosting procedure. By doing so, we can benefit from flexible and interpretable models, which include an automatic variable selection. We compare our approach with three benchmark methods on both aggregated and disaggregated scales using a smart meter data set collected from 3639 households in Ireland at 30-min intervals over a period of 1.5 years. The empirical results demonstrate that our approach based on quantile regression provides better forecast accuracy for disaggregated demand, while the traditional approach based on a normality assumption (possibly after an appropriate Box-Cox transformation) is a better approximation for aggregated demand. These results are particularly useful since more energy data will become available at the disaggregated level in the future.en
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.subjectForecastingen
dc.subjectLoad forecastingen
dc.subjectLoad modelingen
dc.subjectPredictive modelsen
dc.subjectProbabilistic logicen
dc.subjectSmart metersen
dc.subjectUncertaintyen
dc.titleForecasting Uncertainty in Electricity Smart Meter Data by Boosting Additive Quantile Regressionen
dc.typeArticleen
dc.contributor.departmentKing Abdullah University of Science and Technology, Thuwal, 23955-6900, Saudi Arabiaen
dc.identifier.journalIEEE Transactions on Smart Griden
dc.contributor.institutionMonash Business School, Clayton, VIC, 3800, Australiaen
kaust.authorTaieb, Souhaib Benen
kaust.authorHuser, Raphaëlen
kaust.authorGenton, Marc G.en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.