The invention discloses a building multi-performance oriented design optimization method, which comprises the steps of 1, determining a
building design decision target and potential influence factorsthereof as an optimization target and an optimization variable respectively, and defining constraint conditions so as to construct an optimization model; 2, obtaining a building performance sample
library with statistical representativeness, wherein the step comprises construction of an optimization variable sample matrix, setting of a building
physical model, construction of a building performance output matrix and construction of a building multi-dimensional input and multi-dimensional output sample matrix; 3, constructing a simplified relation model between the optimization variable and theoptimization target by adopting a
machine learning
algorithm, and taking the simplified relation model as an agent model; and 4, taking the agent model as a
fitness function of an optimization
algorithm, executing building multi-objective optimization, and obtaining a Pareto optimization result. According to the method, the multi-objective optimization process of the building performance can be more scientific and standard, calling of EnergyPlus
software in the optimization process is reduced through the
coupling agent model and the multi-objective
genetic algorithm, and the optimization timeis shortened.