4 th International Conference On Building Energy, Environment A Review on Automatic Generation of Architectural Space Layouts with Energy Performance Optimization T. Du 1 , M. Turrin 1 , S. Jansen 1 , A. van den Dobbelsteen 1 , N. Biloria 2 1 Faculty of Architecture and the Built Environment Delft University of Technology (TU Delft), 2600 AA, the Netherlands 2 Faculty of Design, Architecture and Building University of Technology Sydney (UTS), Broadway, NSW 2007, Australia SUMMARY The space layout design is one of the most important phases of the architectural design, and the automatic generation of space layout has shown great potential as a design aid. Research has shown that space layouts can have a significant impact on the improvement of energy performance. The combination of the automatic generation of space layout and the optimization of energy performance is expected to be greatly helpful for the development of an energy efficient design in the early design phase. This paper presents a literature review of the current research about the automatic generation of space layout related to the energy performance. The following conclusions can be drawn: space layouts have an important impact on the thermal performance of buildings; only several researches have tried to combine automatic generation of space layout with the energy performance optimization; an in-depth investigation into achievements of past researchers on automatic space layout generation integrated with energy performance optimization is thus promising. Besides, these investigations have resulted in outlining several challenges such as: the calculation of the energy performance lacks the integration of different aspects of energy performance; the current automatically generated space layouts lack the flexibility of shapes, and its application in 3D geometry is limited; the generation of space layouts lack the consideration of specific characters of different types of buildings. KEY WORDS space layout, automatic generation, computer-aided design, energy performance, optimization design INTRODUCTION Architectural space layout design is a stage within the architectural design process that takes place between the “schematic design” phase and the “design development” phase. The space layout design is one of the most important phases of the architectural design, which is relevant to all physical design problems (Michalek et al. 2002). The space layout design is a process to assign relationships to a given function and then a geometry to this function, during which architects translate the client’s needs into an ar chitectural programmatic language (Lobos and Donath 2010). Spatial layout is concerned with finding feasible locations and dimensions for a set of interrelated objects that meet all design requirements and maximize design quality regarding design preferences (Michalek et al. 2002). Different properties of space layout have been researched, including layouts for vision accessibility (Penn and Turner 2003), physical activity (Zimring et al. 2005), occupant behaviour (Goldstein et al. 2011), etc. The Space and Organization Workshop (SPORG) at MIT’s School of Architecture and Planning, created in 1990, is explicitly directed towards exploring the interdependence between physical space and organizational behaviour (Horgen 1999). As for the physical performance, Hsu (2000) creates a database with the relationships between spaces and the surrounding (site, sun, light, wind). Space layout, in addition to the common engineering objectives such as cost and aesthetic, is especially concerned with usability qualities and performance (Michalek and Papalambros 2002). The automatic generation of space layouts uses computational processes to generate designs (Lobos and Donath 2010). There are numerous works focusing on different methods for automatically generated architectural space layouts, and many solutions have been presented and discussed: prototypes, tests, depth computer programming, and optimization formulas embedded in the architectural field (Lobos and Donath 2010). Various studies have been conducted, which show that the automatic generation of space layout has great potential to support architectural design. We especially see potential making buildings net zero energy or energy producing. The rest of the paper is structured as follows. In section 2, the different methods of automatic generation of space layouts are presented. In section 3, the relationship between space layouts and energy performance is discussed. Section 4 provides conclusions and future research directions to be investigated. AUTOMATIC GENERATION OF SPACE LAYOUT Research on the automatic space layout generation started around 50 years ago (Levin 1964). Since then, plenty of studies have been conducted. The outcomes show great potential and serve as inspiration for architects. Kornberger and Clegg (2004) also discussed the relationship between generation and organisational function, which implies that generation will inspire greater possibilities of space layouts, rather than being a passive container. In common, there are basic criteria or constraints that space layouts should satisfy. These can be roughly divided into typology and geometry (Medjdoub and Yannou 2000; Rodrigues et al. 2013b). The geometric constraints include the dimensional requirements for different spaces, like width, length or height. The typological constraints include the adjacencies to different spaces and also to the perimeter of the building, and exterior orientation. There are numerous works focusing on the problem of automatically identifying optimal architectural layout configurations with different methods. According to the ISBN: 978-0-646-98213-7 COBEE2018-Paper283 page 856