Genetic Algorithm-Based Multiobjective Optimization for Building Design

Large-scale building design is a constantly evolving process where design managers are always trying to identify means of producing a 'better' product in a 'shorter' period of time. Hence there is a need for design tools that can help designers better manage collaborative design development. It is becoming difficult to improve the performance of building design based only on improvements in individual disciplines. For this reason, better, system-orientated, holistic, multidisciplinary approaches to building design are needed. This article investigates the applicability of a multidisciplinary design optimization (MDO) methodology in building design. MDO methods divide a single system into a group of smaller subsystems to effectively manage interactions between them. In the context of building design, the system refers to building design as a whole, whereas subsystems represent the various design disciplines or parts of the building, for example spatial zones. Such an approach could reduce the time and cost associated with the multidisciplinary design cycle. As an outcome of this research, a Pareto genetic algorithm-based collaborative optimization (PGACO) framework is developed to support interactions between multiple disciplinary tasks and to coordinate conflicting design objectives. The article demonstrates how the PGACO framework can be applied to a multiobjective multidisciplinary optimization problem. The framework is also tested on a simple mathematical example.