000203769 001__ 203769
000203769 005__ 20190317000049.0
000203769 037__ $$aCONF
000203769 245__ $$aForecasting Uncertainty in Electricity Demand
000203769 269__ $$a2015
000203769 260__ $$c2015
000203769 336__ $$aConference Papers
000203769 520__ $$aGeneralized Additive Models (GAM) are a widely popular class of regression models to forecast electricity demand, due to their high accuracy, flexibility and interpretability. However, the residuals of the fitted GAM are typically heteroscedastic and leptokurtic caused by the nature of energy data. In this paper we propose a novel approach to estimate the time-varying conditional variance of the GAM residuals, which we call the GAM^2 algorithm. It allows utility companies and network operators to assess the uncertainty of future electricity demand and incorporate it into their planning processes. The basic idea of our algorithm is to apply another GAM to the squared residuals to explain the dependence of uncertainty on exogenous variables. Empirical evidence shows that the residuals rescaled by the estimated conditional variance are approximately normal. We combine our modeling approach with online learning algorithms that adjust for dynamic changes in the distributions of demand. We illustrate our method by a case study on data from RTE, the operator of the French transmission grid.
000203769 6531_ $$aforecasting
000203769 6531_ $$ageneralized addtive model
000203769 6531_ $$auncertainty
000203769 6531_ $$aelectricity demand
000203769 6531_ $$aonline learning
000203769 6531_ $$asmart meter data analytics
000203769 700__ $$0245593$$g211617$$aWijaya, Tri Kurniawan
000203769 700__ $$aSinn, Mathieu
000203769 700__ $$aChen, Bei
000203769 7112_ $$dJanuary 26, 2015$$cAustin, TX, USA$$aAAAI-15 Workshop on Computational Sustainability
000203769 8564_ $$uhttps://github.com/tritritri/uncertainty$$zURL
000203769 8564_ $$uhttps://infoscience.epfl.ch/record/203769/files/10104-43110-1-SM.pdf$$zPostprint$$s1152979$$yPostprint
000203769 8564_ $$uhttps://infoscience.epfl.ch/record/203769/files/poster.pdf$$zPoster$$s1099881$$yPoster
000203769 8564_ $$uhttps://infoscience.epfl.ch/record/203769/files/presentation.pdf$$zPresentation$$s986616$$yPresentation
000203769 909C0 $$xU10405$$0252004$$pLSIR
000203769 909CO $$qGLOBAL_SET$$pconf$$ooai:infoscience.tind.io:203769$$pIC
000203769 917Z8 $$x211617
000203769 917Z8 $$x211617
000203769 937__ $$aEPFL-CONF-203769
000203769 973__ $$rREVIEWED$$sACCEPTED$$aEPFL
000203769 980__ $$aCONF