RUB » Bibliotheksportal

Max Benjamin Zorn

• This paper presents a novel, more flexible and faster software framework for design space exploration (DSE) in Rhino/Grasshopper, that allows users to sample the design space, train and deploy machine-learning (ML) models, and visually and interactively explore the design space, and evaluates it with a case study. In light of the climate crisis, the integration of simulation-based optimization processes in the design of buildings is becoming ever more important. Architectural design optimization can effectively reduce a building’s climate impact by, e.g. minimizing energy consumption. However, these optimizations rely on costly simulations and present the designers with only a limited selection of feasible design candidates, i.e. the result of the optimization algorithm. If the so explored well performing design variates do not fulfill other criteria, such as aesthetics, the designers are likely to disregard the optimization results. This is where DSE tools come into play. By utilizing ML to estimate the performance values instead of simulating, and visualizing the results in intuitive ways, designers can be informed of a design variate’s performance in real-time.