| Title |
Sensitivity Analysis Using Explainable AI for Building Energy Use |
| Authors |
추한경(Chu, Han-Gyeong) ; 신한솔(Shin, Han-Sol) ; 조성권(Cho, Seong-Kwon) ; 유영서(Yoo, Young-Seo) ; 박철수(Park, Cheol-Soo) |
| DOI |
https://doi.org/10.5659/JAIK.2022.38.11.279 |
| Keywords |
Explainable AI; Sensitivity analysis; Building energy; Surrogate model |
| Abstract |
Classical sensitivity methods such as Morris and Sobol methods have been widely used in the decision making of building design and
retrofit. However, these methods require a large number of samples to obtain reliable results as well as detailed information on input
variables. On the other hand, the explainable AI technique can convert the relationship between input and output variables to a degree that
can be understood by humans as well as provide more meaningful sensitivity analysis results for rational decision-making. In this paper, three
XAI-based analyses were selected including Feature Importance, LIME, and SHAP. The five methods of Morris, Sobol, Feature Importance,
LIME, and SHAP were applied to a medium office building provided by US DOE. As a result, it was found that XAI-based sensitivity
analyses could provide better results than the classical methods. |