A three-stage optimization methodology for envelope design of passive house considering energy demand, thermal comfort and cost

Abstract

Due to reducing the reliance of buildings on fossil fuels, Passive House (PH) is receiving more and more attention. It is important that integrated optimization of passive performance by considering energy demand, cost and thermal comfort. This paper proposed a set three-stage multi-objective optimization method that combines redundancy analysis (RDA), Gradient Boosted Decision Trees (GBDT) and Nondominated sorting genetic algorithm (NSGA-II) for PH design. The method has strong engineering applicability, by reducing the model complexity and improving efficiency. Among then, the GBDT algorithm was first applied to the passive performance optimization of buildings, which is used to build meta-models of building performance. Compared with the commonly used meta-model, the proposed models demonstrate superior robustness with the standard deviation at 0.048. The optimization results show that the energy-saving rate is about 88.2% and the improvement of thermal comfort is about 37.8% as compared to the base-case building. The economic analysis, the payback period were used to integrate initial investment and operating costs, the minimum payback period and uncomfortable level of Pareto frontier solution are 0.48 years and 13.1%, respectively. This study provides the architects rich and valuable information about the effects of the parameters on the different building performance.

Impact of adjustment strategies on building design process in different climates oriented by multiple performance

“…For example, Wang et al applied the Gradient boosted decision trees (GBDT) algorithm to construct meta-models of building performance. The comparison with ANN and SVR highlights its superior accuracy [24].…”

“…Monte Carlo analysis includes three important parts: (1) specify distributions of the input variables, (2) select the sampling algorithm, and (3) create and run building performance models. In building design, the uniform distribution is commonly used in presenting possible changes in various design parameters [24]. The sampling algorithm is used to obtain the combinations of input variable values from probability density functions, the random sampling [25], Latin hypercube sampling (LHS) [26], and Sobol sequence [5] have been used in the building performance field.…”

“…Building performance optimization is usually a multi-scientific cross-cutting problem involving multiple performance indicators. Due to the inconsistent dimensions between each building performance, such as energy demand indicators and comfort indicators, it is difficult to integrate them into one goal [24]. For such problems, the Pareto method is a suitable choice [40].…”

“…The detailed construction process of this algorithm is described in reference [64]. The main parameters affecting GBDT performance are the maximum depth of trees (MD), the number of trees (N), and the maximum of features (MF) [24]. The accuracy indicators specified in ASHRAE Guideline 14-2002 can be introduced to evaluate the performance of meta-models.…”

Analysis of the Applicability of Non-Destructive Techniques to Determine In Situ Thermal Transmittance in Passive House Façades

“…Nearly Zero Energy Buildings (NZEBs) have become an essential element in developed countries to achieve a reduction in energy consumption and CO 2 in the construction sector [4][5][6], using efficient systems of HVAC (Heating, Ventilating, and Air-Conditioning) and increasing the thermal insulation of buildings [7]. Indeed, PH requires 80-90% less heating energy than conventional buildings to provide optimal thermal comfort conditions, while the initial investment only represents an increase of 5-10% [8]. However, the main barriers for this type of construction are the high performance building materials and the cost of adoption (training and certification) [9,10].…”