Developing surrogate models for the early-stage design of residential blocks using graph neural networks
Open Access
- 22 January 2025
- journal article
- research article
- Published by Springer Nature in Building Simulation
- Vol. 18 (3) , 679-698
Abstract
Building simulation based on physical modeling is commonly adopted for performance prediction, but the high time costs hinder its application in the early design stage of buildings. Data-driven surrogate models have been proposed as a means to replicate computationally expensive simulation models. However, existing surrogate models for sustainable residential block design are limited in scope, focusing either on individual buildings or on specific cases within multi-block projects. This study leverages graph neural networks to develop optimal surrogate models incorporating inter-building effects to predict multiple indicators of sustainable performance for residential blocks at a region level. A graph schema is proposed to represent the general geometric features and relations among buildings in residential block design. A regional dataset is generated for model training and testing, using real residential zones in Hong Kong. The surrogate models are developed and evaluated, using two kinds of architectures (individual architectures for specific indicators and an integrative architecture) and three different neural networks (graph attention network (GAT), graph convolutional network, and artificial neural network). The results showed that the surrogate models using the individual architectures and GAT outperform the models using other architectures and neural networks. These surrogate models achieve a high prediction accuracy with CV(RMSE)s of 11.79%, 7.63%, and 8.00% in terms of energy consumption, indoor thermal comfort, and daylighting, respectively, on the regional test set. Moreover, they enable a significant acceleration of the performance evaluation, reducing the calculation time from 6.346 min to 1.565 ms (243,297 times) per case compared to physics-based simulations.Keywords
This publication has 47 references indexed in Scilit:
- A knowledge-informed optimization framework for performance-based generative design of sustainable buildingsApplied Energy, 2024
- An integrated framework for residential layout designs: Combining parametric modeling, neural networks, and multi-objective optimization for outdoor activity space optimizationAlexandria Engineering Journal, 2023
- Graph convolutional networks-based method for estimating design loads of complex buildings in the preliminary design stageApplied Energy, 2022
- Exploring graph neural networks for semantic enrichment: Room type classificationAutomation in Construction, 2022
- Times series forecasting for urban building energy consumption based on graph convolutional networkApplied Energy, 2022
- Building energy performance assessment using linked data and cross-domain semantic reasoningAutomation in Construction, 2021
- Graph neural networks: A review of methods and applicationsAI Open, 2020
- The parametric based optimization framework daylighting and energy performance in residential buildings in hot arid zoneAlexandria Engineering Journal, 2018
- Brick : Metadata schema for portable smart building applicationsApplied Energy, 2018
- An object-oriented framework for simulation-based green building design optimization with genetic algorithmsAdvanced Engineering Informatics, 2005