Multi-objective optimization for gymnasium layout in early design stage: Based on genetic algorithm and neural network

The layout of gymnasium directly affects environment performance. The current methods are insufficient to provide quantified decision support for gymnasium layouts in the early design stages (EDS). This study proposes a framework for optimizing the layout of gymnasiums using a multi-objective optimization (MOO) method based on genetic algorithms (GA) and neural networks. The study tested the framework using a community sports arena as an example, and the results indicate: the final optimized solutions achieved a maximum reduction of 11.1 % in cooling energy consumption (CE) and 3.3 % in solar radiation (SR) compared to the earlier generations, along with a 0.9 % improvement in thermal comfort percentage (TCP). This framework promotes the development of algorithm-driven methods for stadium layout design, while the prediction model based on RBF neural networks can simultaneously provide effective performance predictions for similar design outcomes.