This document discusses using design of experiments to optimize the energy consumption of a 3-story office building in New Delhi. It involves 4 phases: 1) An experimental setup identifies 26 design variables and runs 352 simulations. 2) ANOVA identifies significant variables affecting lighting/cooling energy. 3) Response surface models are developed and validated via Latin hypercube sampling. 4) Optimization techniques like genetic algorithms are applied to minimize lifecycle costs and energy use, identifying optimal designs. The methodology shows design of experiments can efficiently screen variables and create surrogates that optimize building design faster than simulation alone.