Real-time prediction of workplane illuminance distribution for daylight-linked controls using non-intrusive multimodal deep learning
This addresses energy savings in buildings by enabling accurate real-time predictions for dynamically occupied spaces, though it is incremental as it builds on existing deep learning methods for daylight prediction.
The study tackled real-time prediction of indoor workplane illuminance distribution for daylight-linked controls by proposing a non-intrusive multimodal deep learning framework, achieving high accuracy with R2 > 0.98 and RMSE < 0.14 on same-distribution tests and R2 > 0.82 on unseen-day tests.
Daylight-linked controls (DLCs) have significant potential for energy savings in buildings, especially when abundant daylight is available and indoor workplane illuminance can be accurately predicted in real time. Most existing studies on indoor daylight predictions were developed and tested for static scenes. This study proposes a multimodal deep learning framework that predicts indoor workplane illuminance distributions in real time from non-intrusive images with temporal-spatial features. By extracting image features only from the side-lit window areas rather than interior pixels, the approach remains applicable in dynamically occupied indoor spaces. A field experiment was conducted in a test room in Guangzhou (China), where 17,344 samples were collected for model training and validation. The model achieved R2 > 0.98 with RMSE < 0.14 on the same-distribution test set and R2 > 0.82 with RMSE < 0.17 on an unseen-day test set, indicating high accuracy and acceptable temporal generalization.