This document outlines a methodology for building energy simulation optimization that includes global sensitivity analysis (GSA), surrogate modeling (SM), and genetic algorithm (GA) optimization. A case study applies this methodology to a building model with 26 design variables. GSA identifies significant variables for lighting and cooling energy. SM builds response surface models to approximate simulation outputs based on significant variables. GA optimization then uses the SM to efficiently search for optimal designs. Validation shows SM predictions are within 10% error of simulations. The methodology enables faster optimization of building designs compared to directly coupling simulation with optimization.