GEFCOM 2014 - Probabilistic Electricity Price Forecasting
This work addresses energy price forecasting for electricity markets, but it is incremental as it compares existing methods without introducing new techniques.
The paper tackled probabilistic electricity price forecasting by comparing ARMA with exogenous variables and Gradient Boosting Regression on GEFCOM 2014 data, finding that a multi-model approach significantly improved error metrics, with Gradient Boosting achieving lower normalized mean absolute error.
Energy price forecasting is a relevant yet hard task in the field of multi-step time series forecasting. In this paper we compare a well-known and established method, ARMA with exogenous variables with a relatively new technique Gradient Boosting Regression. The method was tested on data from Global Energy Forecasting Competition 2014 with a year long rolling window forecast. The results from the experiment reveal that a multi-model approach is significantly better performing in terms of error metrics. Gradient Boosting can deal with seasonality and auto-correlation out-of-the box and achieve lower rate of normalized mean absolute error on real-world data.