An integrated building energy performance evaluation method: From parametric modeling to GA-NN based energy consumption prediction modeling

Building energy performance evaluation, as an important process in a sustainable building design, has consequences for global conservation and environmental protection. The traditional methods to perform this evaluation are usually time-consuming computationally complex, have high requirements designers’ professional knowledge on architectural physics software operation skills. To solve these problems provide rapid, user-friendly, more accurate prediction results, study presents efficient method which integrates information modeling, simulation, consumption together. This follows three-stage research framework: Stage 1 proposes rapid 3D modeling according the parameterized setting, 2 generates numerous simulation results automatically by EnergyPlus, 3 develops user-friendly model with help of Genetic Algorithm-Neural Network (GA-NN) provides level design after prediction. A case is carried out present overall verify accuracy proposed method. contributes improvement both extensive dataset establishment operational efficiency It can designers real-time, reliable tool assessment basis phase construction projects.