Quantile Regression for Qualifying Match of GEFCom2017 Probabilistic Load Forecasting
This work addresses probabilistic load forecasting for energy systems, but it is incremental as it applies a known quantile regression technique with specific tweaks to a competition dataset.
The authors tackled probabilistic load forecasting by developing a simple quantile regression method that accounts for weekly and annual seasonalities, ignoring public holidays and using temperature only for trend stabilization. Their approach placed second in the open data track and fourth in the definite data track of GEFCom2017, outperforming a benchmark consistently.
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.