AbstractThe paper describes different mathematical models and real-time predictors of the short-term winter electric load in the biggest Italian district. First it is ascertained that weather variables such as temperature and illumination actually affect the load. Their maximum impact is quantified in 6% in a winter workday. However, when forecasting the load in real time, the use of the exogenous weather inputs can be surrogated by a careful modelling of the autoregressive predictor component and by applying recursive parameter estimation techniques like exponential weighting.