Forecasting indoor temperatures during heatwaves: Do more complex models provide better predictions?

A novel application of semi-parametric Generalized Additive Models (GAMs) was developed to forecast elevated indoor temperatures. GAM models were compared to AutoRegressive models with eXogenous inputs (ARX) and validated against monitored data from two case study dwellings, located near to Loughborough in the UK, during the 2013 heatwave. Input variables were selected using backward stepwise regressions based on minimisation of the Akaike Information Criterion (AIC) and Mean Absolute Error (MAE), for the ARX and GAM models respectively. Comparison of the models showed that GAMs are capable of slightly improving the forecasting accuracy, but only at short horizons (3-6 hours ahead).