Ensembling methods for countrywide short term forecasting of gas demand
This work addresses gas demand forecasting for energy operators, but it is incremental as it applies standard ensemble techniques to a specific dataset.
The study tackled one-day-ahead gas demand forecasting in Italy by comparing nine base models and four ensemble methods, finding that ensembles consistently outperformed base models and beat Transmission System Operator predictions in a two-year out-of-sample validation.
Gas demand is made of three components: Residential, Industrial, and Thermoelectric Gas Demand. Herein, the one-day-ahead prediction of each component is studied, using Italian data as a case study. Statistical properties and relationships with temperature are discussed, as a preliminary step for an effective feature selection. Nine "base forecasters" are implemented and compared: Ridge Regression, Gaussian Processes, Nearest Neighbours, Artificial Neural Networks, Torus Model, LASSO, Elastic Net, Random Forest, and Support Vector Regression (SVR). Based on them, four ensemble predictors are crafted: simple average, weighted average, subset average, and SVR aggregation. We found that ensemble predictors perform consistently better than base ones. Moreover, our models outperformed Transmission System Operator (TSO) predictions in a two-year out-of-sample validation. Such results suggest that combining predictors may lead to significant performance improvements in gas demand forecasting.