Forecasting residential gas demand: Machine learning approaches and seasonal role of temperature forecasts

The one-day-ahead forecasting of residential gas demand at country level is investigated by implementing and comparing five models: ridge regression, Gaussian process (GP), k-nearest neighbour, artificial neural network (ANN) and torus model. Italian demand data are used for testing the proposed algorithms. The most significant aspects of the pre-processing and feature engineering are discussed, lending particular attention to the role of one-day-ahead temperature forecasts. Our best model, in terms of root mean square error (RMSE), is the ANN; if the mean absolute error (MAE) is considered, the GP becomes the best model, although by a narrow margin. A novel contribution is the development of a model describing the propagation of temperature forecast errors to gas forecasting errors that is successfully validated on data. On the Italian data, it is shown that temperature errors account for 18% of the mean square error of gas demand forecasts