Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
398263 | International Journal of Electrical Power & Energy Systems | 2016 | 13 Pages |
•Regression models with functional response are proposed to forecast daily curves of electricity demand and price.•A comparative study, including results from models with functional or scalar response, is reported.•The proposed models result very competitive.
The features of the electricity, as well as the rules of the competitive electricity markets, create the need of accurate predictions of electricity demand and price in order to anticipate decisions. Mainly, the prediction task in energy markets has been studied in the literature with the aim of obtaining scalar (hourly, daily, …) forecasts given scalar (and/or, less frequently, functional) historical data. This paper provides two methods to predict next-day electricity demand and price daily curves given information from past curves. They are based on using robust functional principal component analysis and nonparametric models with functional both response and covariate. In addition, the nonparametric proposal is extended to incorporate, in a linear way, exogenous scalar covariates. Results of these methods for the electricity market of mainland Spain, in year 2012, are reported. Their accuracy is compared with that of a naïve method as well as with the corresponding to combining forecasts. Scalar versions are also included in the comparative study. This work extends and complements the methods and results in Vilar et al. (2012), focused on scalar forecasts.