Time-cost optimization at the conceptual design stage using differential evolution

Abstract

Concurrent minimization of construction cost and duration is a challenging task for architects through conceptual design. Using differential evolution (DE) this study aims to obtain optimum design solutions that minimize unit cost of construction and construction duration. Single family housing projects in Germany is sampled with the intent of developing objective functions with regression analysis. The results suggests that DE is able to converge a set of optimum design solutions after adequate number of generations. Resemblance between descriptive statistics of the sampled observations and DE results underpins that regression models can be employed to develop objective functions in the presence of reliable and structured data. In addition results by the formal test of hypothesis based on hypervolume indicator offers DE/rand/1/bin outperforms DE/rand/2/bin irrespective of building standard. Last but not least solutions offered by DE allows us to discuss insights regarding design economics. © 2017 Elsevier B.V. All rights reserved.