TY - GEN
T1 - Comparative Analysis of Machine Learning Models Optimized by Bayesian Algorithm for Indoor Daylight Distribution Prediction
AU - Shen, Unhai
AU - Han, Yunsong
N1 - Publisher Copyright:
© PLEA 2020 - 35th PLEA Conference on Passive and Low Energy Architecture Planning Post Carbon Cities, Proceedings.
PY - 2020
Y1 - 2020
N2 - Daylight distribution evaluation is vital for daylight design. However, its application in the early design stage is limited due to the time-consuming simulation process. Many statistical models were proposed to reduce the prediction time, yet application of the machine learning model in daylight prediction was relatively rare and has very limited generalization capability. This paper aims to propose a new workflow for indoor daylight distribution prediction, and compare the performance of XGB, RF, SVR and MLP models with Bayesian optimization. The results showed the MLP based prediction model achieved best generalization performance for indoor daylight prediction, which reduced the simulation time to less than 1 second and maintained satisfactory accuracy.
AB - Daylight distribution evaluation is vital for daylight design. However, its application in the early design stage is limited due to the time-consuming simulation process. Many statistical models were proposed to reduce the prediction time, yet application of the machine learning model in daylight prediction was relatively rare and has very limited generalization capability. This paper aims to propose a new workflow for indoor daylight distribution prediction, and compare the performance of XGB, RF, SVR and MLP models with Bayesian optimization. The results showed the MLP based prediction model achieved best generalization performance for indoor daylight prediction, which reduced the simulation time to less than 1 second and maintained satisfactory accuracy.
KW - Artificial Neural Network
KW - Bayesian Optimization
KW - Daylight Distribution Prediction
KW - Machine Learning
KW - UDI
UR - https://www.scopus.com/pages/publications/85173558477
M3 - 会议稿件
AN - SCOPUS:85173558477
T3 - PLEA 2020 - 35th PLEA Conference on Passive and Low Energy Architecture Planning Post Carbon Cities, Proceedings
SP - 988
EP - 993
BT - PLEA 2020 - 35th PLEA Conference on Passive and Low Energy Architecture Planning Post Carbon Cities, Proceedings
A2 - Alvarez, Jorge Rodriguez
A2 - Goncalves, Joana Carla Soares
A2 - Goncalves, Joana Carla Soares
A2 - Goncalves, Joana Carla Soares
PB - University of A Coruna and Asoc
T2 - 35th PLEA Conference on Passive and Low Energy Architecture Planning Post Carbon Cities, PLEA 2020
Y2 - 1 September 2020 through 3 September 2020
ER -