Reducing energy consumption while providing a high-quality environment for building occupants has become an important target worthy of consideration in the pre-design stage. A reasonable design can achieve both better performance and energy conservation. Parametric design tools show potential to integrate performance simulation and control elements into the early design stage. The large number of design scheme iterations, however, increases the computational load and simulation time, hampering the search for optimized solutions. This paper proposes an integration of parametric design and optimization methods with performance simulation, machine learning, and algorithmic generation. Architectural schemes were modeled parametrically, and numerous iterations were generated systematically and imported into neural networks. Generative Adversarial Networks (GANs) were used to predict environmental performance based on the simulation results. Then, multi-object optimization can be achieved through the fast evolution of the genetic algorithm binding with the database. The test case used in this paper demonstrates that this approach can solve the optimization problem with less time and computational cost, and it provides architects with a fast and easily implemented tool to optimize design strategies based on specific environmental objectives.
Reducing energy consumption while providing a high-quality environment for occupants has become an important target which is worthy of consideration in the pre-design stage. A reasonable design can help achieve better performance while avoiding too much energy consumption. Parametric design tools show the potential to integrate performance simulation and control elements into the early design stage. However, a large amount of the design scheme iterations increases the computational load and simulation time, bringing difficulties in searching for optimized solutions. This paper proposes a methodology containing parametric design and optimization methods integrated with performance simulation, machine learning, and generation algorithm. Architectural schemes were modeled with parametric variables, and numerous iterations were generated systematically and imported into neural networks. Generative Adversarial Network (GAN) is used in machine learning when training to predict environmental performance based on the images of simulation results. Then multi-object optimization can be achieved through the fast evolution of the genetic algorithm binding with the database. The case test used in this paper demonstrates this approach can solve the optimization problem with less time and computational cost, and provides architects with a fast and easily implemented tool to optimize design strategies based on specific environmental objectives.