A metamodel-based multi-objective optimization method to balance thermal comfort and energy efficiency in a campus gymnasium

• Published in: Energy and buildings Vol. 253; p. 111513
• Main Authors: Yue, Naihua, Li, Lingling, Morandi, Alessandro, Zhao, Yang
• Format: Journal Article
• Language: English
• Published: Lausanne Elsevier B.V 15.12.2021; Elsevier BV
• Subjects: Absorptance; Absorptivity; Air conditioning; Algorithms; Artificial neural networks; Building design; Configuration management; Cooling; Design factors; Design optimization; Energy consumption; Energy efficiency; External walls; Genetic algorithms; Green buildings; Gymnasium; Heating; Hypercubes; Metamodels; MLPANN; Multi-objective optimization; Multilayers; Multiple objective analysis; Neural networks; NSGA-II; Pareto optimization; Principal components analysis; Public buildings; Sorting algorithms; Thermal comfort; Ventilation; NSGA-II; Energy consumption; MLPANN; Thermal comfort; Multi-objective optimization; Gymnasium
• ISSN: 0378-7788; 1872-6178
• DOI: 10.1016/j.enbuild.2021.111513

•A method for the metamodel-based multi-objective optimization of large space building, taking advantage of high performance computing, was developed.•An actual campus gymnasium in Qingdao, China was the case study.•The normalized degree-hours for naturally-ventilated seasons and the energy consumption for air-conditioning seasons were the objective functions.•The energy consumption, thermal comfort and the optimization time of case study was drastically improved. Performing multi-objective optimization for actual public building design has become one of the most challenging subjects in buildings energy efficiency area. Gymnasium is a large energy consumer in public buildings. This study efforts to put forward a novel approach to tackle multi-objective optimization problems for building performance of Qingdao University (QUT) Gymnasium using a new metamodel method. For this purpose, the Nondominated Sorting Genetic Algorithm-II (NSGA-II) was dynamically combined with Multilayer Perception Artificial Neural Network (MLPANN) metamodel, which was previously trained with the co-simulation results conducted using EnergyPlus and Eppy. The new research method also proposes an optimal algorithm coupling Latin Hypercube Sample (LHS) with Principal Component Analysis (PCA) to minimize the total training samples, and guarantees the accuracy of optimization results. The most influential design factors like internal and external wall types, roof types, solar absorptance, windows shading as well as night ventilation (NV) strategy and displacement ventilation (DV) air conditioning system of the gymnasium were considered in three cases of 4×108 possibilities to obtain the optimal trade-off results (Pareto front) between energy consumption and thermal comfort. Finally, a normalized minimum distance decision method was adopted to choose the optimal design configuration from the Pareto front. The optimization results of the study cases showed that reductions were achieved not only in the normalized objectives (88.0% less fh and 85.3% less fc) but also in the sub-objectives: up to 78.2% fewer heating energy and 71.3% fewer cooling energy in air conditioning seasons, and up to 97.7% less heating degree-hours and 99.2% less cooling degree-hours in naturally-ventilated seasons, compared to the original configuration by using optimal design takes simultaneous advantage of NV and DV strategies. The method was confirmed to be an efficient and robust tool for gymnasium design, it could reduce the calculation time of whole optimization process from 10 months to 2 days.