Comparison of Factorial and Latin Hypercube Sampling Designs for Meta-Models of Building Heating and Cooling Loads

Interest in research analyzing and predicting energy loads consumption the early stages of building design using meta-models has constantly increased recent years. Generally, it requires many simulated or measured results to build meta-models, which significantly affects their accuracy. In this study, Latin Hypercube Sampling (LHS) is proposed as an alternative Fractional Factor Design (FFD), since can improve accuracy while including nonlinear effect parameters with a smaller size data. Building office floor ten were selected meta-models’ objectives, developed two sampling methods. The heating/cooling for designs was compared. For considered ranges parameters, window insulation (WDI) Solar Heat Gain Coefficient (SHGC) found have characteristics on cooling heating loads. LHS showed better prediction compared FFD, considers impacts given number treatments. It always good idea use over FFD treatments, existence nonlinearity relation not pre-existing information.