A gap-filling method for room temperature data based on autoencoder neural networks

This study explores the applicability of a deep learning-based approach for reconstructing missing room temperature data from different domains where relatively few training samples are available. For that purpose, existing convolutional, long short-term memory (LSTM) and feed-forward autoencoders were combined with suitable domain adaptation procedure. Eventually, developed models evaluated on collected in four buildings significant differences thermal mass, design location. The findings pointed out can be conducted efficiently by using small sample target domain. Additionally, results showed proposed model reconstruct up to 80 % daily inputs RMSE accuracy 0.6 °C.