This study performs a quantitative assessment of transfer learning-based methods for 24-h ahead building energy predictions. 

Technology Overview
Transfer learning has been utilized for short-term building energy predictions. The potentials of transfer learning have been evaluated in two learning scenarios. Different implementation strategies have been tested for energy predictions. The value of transfer learning has been validated through statistical assessments. It helps to develop transfer learning-based methods for building energy management.

Applications & Benefits
This research validates the value of transfer learning in short-term building energy predictions. It can provide practical guidelines when developing transfer learning-based solutions for analyzing massive building operational data. Future studies will be conducted to investigate the potential of transfer learning in different building tasks (e.g., fault detection and diagnosis), using different source data availabilities (e.g., using 20% rather than 80% of the buildings as the source domain), and developing high-level strategies for knowledge transfer (e.g., taking into account the similarity between source and target buildings for knowledge transfer).

Abstract：
The wide availability of massive building operational data has motivated the development of advanced data-driven methods for building energy predictions. Existing data-driven prediction methods are typically customized for individual buildings and their performance are highly influenced by the training data amount and quality. In practice, buildings may only possess limited measurements due to the lack of advanced monitoring systems or data accumulation time. As a result, existing data-driven approaches may not present sufficient values for practical applications. A novel solution can be developed based on transfer learning, which utilizes the knowledge learnt from well-measured buildings to facilitate prediction tasks in other buildings. However, the potentials of transfer learning-based methods for building energy predictions have not been systematically examined. To address this research gap, a transfer learning-based methodology is proposed for 24-h ahead building energy demand predictions. Experiments have been designed to investigate the potentials of transfer learning in different scenarios with different implementation strategies. Statistical assessments have been performed to validate the value of transfer learning in short-term building energy predictions. Compared with standalone models, the transfer learning-based methodology could reduce approximately 15% to 78% of prediction errors. The research outcomes are useful for developing advanced transfer learning-based methods for typical tasks in building energy management. The insights obtained can help the building industry to fully realize the value of existing building data resources and advanced data analytics.

Statistical investigations of transfer learning-based methodology for short-term building energy predictions
Author：Fan C., Sun Y., Xiao F., Ma J., Lee D., Wang J., Tseng Y.C.
Year：2020
Source publication：Applied Energy  Volume 262, 15 March 2020, 114499
Subfield Highest percentage：99%    Building and Construction    #1/185

https://www.sciencedirect.com/science/article/pii/S0306261920300118