Quantile Regression for Qualifying Match of GEFCom2017 Probabilistic Load Forecasting

Abstract

We present a simple quantile regression-based forecasting method that was applied in a probabilistic load forecasting framework of the Global Energy Forecasting Competition 2017 (GEFCom2017). The hourly load data is log transformed and split into a long-term trend component and a remainder term. The key forecasting element is the quantile regression approach for the remainder term that takes into account weekly and annual seasonalities such as their interactions. Temperature information is only used to stabilize the forecast of the long-term trend component. Public holidays information is ignored. Still, the forecasting method placed second in the open data track and fourth in the definite data track with our forecasting method, which is remarkable given simplicity of the model. The method also outperforms the Vanilla benchmark consistently.

accepted for International Journal of Forecasting

References in corpus (4)

• Day-ahead electricity price forecasting with high-dimensional structures: Univariate vs. multivariate modeling frameworks
• Lasso estimation for GEFCom2014 probabilistic electric load forecasting
• Forecasting wind power - Modeling periodic and non-linear effects under conditional heteroscedasticity
• A hybrid model of kernel density estimation and quantile regression for GEFCom2014 probabilistic load forecasting

Cited by in corpus (2)

• Efficient mid-term forecasting of hourly electricity load using generalized additive models
• State-Space Models Win the IEEE DataPort Competition on Post-covid Day-ahead Electricity Load Forecasting