Using genetic algorithm to automate the generation of an open-plan office layout

Abstract

Today, the concept of open plan is more and more widely accepted that many companies have switched to open-plan offices. Their design is an issue in the scope of space layout planning. Although there are many professional architectural layout design software in the market, in the real life, office designers seldom use these tools because their license fees are usually expensive and using them to solve an open-plan office design is like using an overly powerful and expensive tool to fix a minor problem. Therefore, manual drafting through a trial and error process is most often used. This article attempts to propose a lightweight tool to automate open-plan office layout generation using a nested genetic algorithm optimization with two layers, where the inner layer algorithm is embedded in the outer one. The result is enhanced by a local search. The main objective is to maximize space utilization by maximizing the size of the open workspace. This approach is different from its precedents, in that the location search is conducted on a grid map rather than several pre-selected candidate locations. Consequently, the generated layout design presents a less rigid workstation arrangement, inviting a casual and unrestrictive work environment. The real potential of the approach is reflected in the productivity of test fits. Automating and simplifying the generation of layouts for test fits can tremendously decrease the amount of time and resources required to generate them. The experimental case study shows that the developed approach is powerful and effective, making it a totally automated process.

Research on Space Optimization Design of High-rise Residential Building Based on Genetic Algorithm

“…Each design variable has a certain range, for example, the aspect ratio of the room, the area of the window, the location of the vent, etc. [17][18]. Determine the desired population size, which refers to the number of individuals included in a generation.…”

Adaptable modular construction systems and multi-objective optimisation strategies for mass-customised housing: A new user-driven paradigm for high-rise living in Hong Kong

“…For the final stage of our research-by-design project, the generative process was refined, and the material system further developed to generate more ‘realistic’ outcomes, intended as conversation materials during engagement with Hong Kong housing sector professionals. Further studies of precedent research projects guided how the use of a gridmap can be used to generate assemblies of discretised space into various rooms of different sizes and proportions, 24 including rectangular shapes gives as additional input parameters into the workflow. 25 The computational process was adjusted to use rectangular shaped spaces as initial geometry elements, which were processed through the dynamic force-driven algorithm into a closer packing of neighbouring rooms and adjoining apartments.…”

Generative workplace and space planning in architectural practice

“…The greedy algorithm took proposed input values and attempted to create a floor plan of related spaces as the output. Chen et al 15 attempted to use two nested genetic algorithms to test fit open plan offices that maximized space utilization by minimizing non-functional area. The first algorithm found the best combination of room locations while the second algorithm minimized circulation area.…”