TY - JOUR
T1 - Simulation-based optimization of an integrated daylighting and HVAC system using the design of experiments method
AU - Kim, Wonuk
AU - Jeon, Yongseok
AU - Kim, Yongchan
N1 - Funding Information:
This work was supported by the Human Resources Development Program (No. 20144010200770 ) and the Energy Technology Development Program (No. 20142010102660 ) of the Korea Institute of Energy Technology Evaluation and Planning (KETEP), through a grant funded by the Korea Government Ministry of Trade, Industry and Energy.
Publisher Copyright:
© 2015 Elsevier Ltd.
PY - 2016/1/15
Y1 - 2016/1/15
N2 - The use of daylight in buildings to save energy while providing satisfactory environmental comfort has increased. Integration of the daylighting and thermal energy systems is necessary for environmental comfort and energy efficiency. In this study, an integrated meta-model for a daylighting, heating, ventilating, and air conditioning (IDHVAC) system was developed to predict building energy performance by artificial lighting regression models and artificial neural network (ANN) models, with a database that was generated using the EnergyPlus model. The design of experiments (DOE) method was applied to generate the database that was used to train robust ANN models without overfitting problems. The IDHVAC system was optimized using the integrated meta-model and genetic algorithm (GA), to minimize total energy consumption while satisfying both thermal and visual comfort for occupants. During three months in the winter, the GA-optimized IDHVAC model showed, on average, 13.7% energy savings against the conventional model.
AB - The use of daylight in buildings to save energy while providing satisfactory environmental comfort has increased. Integration of the daylighting and thermal energy systems is necessary for environmental comfort and energy efficiency. In this study, an integrated meta-model for a daylighting, heating, ventilating, and air conditioning (IDHVAC) system was developed to predict building energy performance by artificial lighting regression models and artificial neural network (ANN) models, with a database that was generated using the EnergyPlus model. The design of experiments (DOE) method was applied to generate the database that was used to train robust ANN models without overfitting problems. The IDHVAC system was optimized using the integrated meta-model and genetic algorithm (GA), to minimize total energy consumption while satisfying both thermal and visual comfort for occupants. During three months in the winter, the GA-optimized IDHVAC model showed, on average, 13.7% energy savings against the conventional model.
KW - Artificial neural network (ANN)
KW - Daylighting
KW - Design of experiments (DOE)
KW - Energy efficiency
KW - Genetic algorithm (GA)
KW - Integrated energy system modelling
UR - http://www.scopus.com/inward/record.url?scp=84946429587&partnerID=8YFLogxK
U2 - 10.1016/j.apenergy.2015.10.153
DO - 10.1016/j.apenergy.2015.10.153
M3 - Article
AN - SCOPUS:84946429587
SN - 0306-2619
VL - 162
SP - 666
EP - 674
JO - Applied Energy
JF - Applied Energy
ER -
