TY - JOUR
T1 - Can semi-parametric additive models outperform linear models, when forecasting indoor temperatures in free-running buildings?
AU - Gustin, Matej
AU - McLeod, Robert Scot
AU - Lomas, Kevin J.
PY - 2019/6/15
Y1 - 2019/6/15
N2 - A novel application combining semi-parametric Generalized Additive Models (GAMs) with logistic GAMs was developed to forecast indoor temperatures and window opening states during prolonged heatwaves. 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 whilst GAMs are capable of improving the forecasting accuracy, the improvements are significant only up to 3–6 h ahead. During heatwaves and over longer forecasting horizons, GAMs were found to be less reliable and accurate than ARX models. The marginal improvement in forecasting accuracy at shorter horizons did not justify the additional computational time and risk of instability associated with more complex GAMs, at longer forecasting horizons. Whilst, logistic GAMs were shown to adequately predict the window opening state, incorporating knowledge of the window state did not significantly improve the accuracy of the indoor temperature predictions.
AB - A novel application combining semi-parametric Generalized Additive Models (GAMs) with logistic GAMs was developed to forecast indoor temperatures and window opening states during prolonged heatwaves. 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 whilst GAMs are capable of improving the forecasting accuracy, the improvements are significant only up to 3–6 h ahead. During heatwaves and over longer forecasting horizons, GAMs were found to be less reliable and accurate than ARX models. The marginal improvement in forecasting accuracy at shorter horizons did not justify the additional computational time and risk of instability associated with more complex GAMs, at longer forecasting horizons. Whilst, logistic GAMs were shown to adequately predict the window opening state, incorporating knowledge of the window state did not significantly improve the accuracy of the indoor temperature predictions.
KW - Time series forecasting
KW - Generalized Additive Model (GAM)
KW - AutoRegressive model with eXogenous inputs (ARX)
KW - Logistic GAM
KW - Window opening state
KW - Heatwave
KW - Overheating
KW - Indoor temperature
UR - http://dx.doi.org/10.1016/j.enbuild.2019.03.048
U2 - 10.1016/j.enbuild.2019.03.048
DO - 10.1016/j.enbuild.2019.03.048
M3 - Article
SN - 0378-7788
VL - 193
SP - 250
EP - 266
JO - Energy and Buildings
JF - Energy and Buildings
ER -