Hybridization of an evolutionary algorithm and simulations of co-evolutionary design processes for early-stage building spatial design optimization

Three methods for early-stage building spatial design optimization are presented, demonstrated, and compared for their qualities and limitations. The first, an evolutionary algorithm, can find well-distributed approximations of the Pareto front, but it uses many design evaluations and it can only explore a limited part of the entire design search space (i.e. the collection of all possible design solutions). The second, simulations of co-evolutionary design processes, can find improved design solutions relatively fast within an unrestricted design search space, however, they typically only find discretely distributed Pareto front approximations. For the third method, hybridization is proposed to combine the first two methods into two new hybrid methods, such that their advantages are combined and their disadvantages are diminished. The methods have been applied in an initial case study, which shows that hybridization can improve search efficiency and speed, and it can search larger design search spaces.

Automated summary

Three methods for early-stage building spatial design optimization are presented, demonstrated, and compared for their qualities and limitations. The first method, an evolutionary algorithm, can find well-distributed approximations of the Pareto front but is limited by the number of design evaluations. The second method, simulations of co-evolutionary design processes, can find improved design solutions relatively fast but typically only find discretely distributed Pareto front approximations. The third method proposes hybridization to combine the advantages of the first two methods and diminish their disadvantages, showing improved search efficiency and speed in a case study.