Multi-Objective Optimization Design for Cold-Region Office Buildings Balancing Outdoor Thermal Comfort and Building Energy Consumption
Open Access
Abstract
Performance parameters and generative design applications have redefined the human–machine collaborative relationship, challenging traditional architectural design paradigms and guiding the architectural design process toward a performance-based design transformation. This study proposes a multi-objective optimization (MOO) design approach based on performance simulation, utilizing the Grasshopper-EvoMass multi-objective optimization platform. The Non-dominated Sorting Genetic Algorithm II (NSGA-II) is applied to coordinate two performance metrics—outdoor thermal comfort and building energy loads—for the multi-objective optimization of architectural design. The results indicate that (1) a performance-based multi-objective optimization design workflow is established. Compared to the baseline design, the optimized building form shows a significant improvement in performance. The Pareto optimal solutions, under 2022 meteorological conditions, demonstrate an annual energy efficiency improvement of 16.55%, and the outdoor thermal neutrality ratio increases by 1.11%. These results suggest that the optimization approach effectively balances building energy loads and outdoor thermal comfort. (2) A total of 1500 building form solutions were generated, from which 16 optimal solutions were selected through the Pareto front method. The resulting Pareto optimal building layouts provide multiple feasible form configurations for the early-stage design phase.Keywords
Funding Information
- National Natural Science Foundation of China (52108044, 2025lslybwzzkt-156)
- Liaoning Province Social Science Federation’s economic and social development project (52108044, 2025lslybwzzkt-156)
This publication has 51 references indexed in Scilit:
- What is generative in generative artificial intelligence? A design-based perspectiveResearch in Engineering Design, 2024
- Multi-objective optimization of energy demand and net zero energy building design based on climatic conditions (Case study: Iran)International Journal of Environmental Science and Technology, 2024
- Evolving multi-objective optimization framework for early-stage building design: Improving energy efficiency, daylighting, view quality, and thermal comfortBuilding Simulation, 2024
- A novel multi-objective generative design approach for sustainable building using multi-task learning (ANN) integrationApplied Energy, 2024
- Multi-objective optimization for energy-efficient building design considering urban heat island effectsApplied Energy, 2024
- Energy consumption simulations of rural residential buildings considering differences in energy use behavior among family membersBuilding Simulation, 2024
- Exploring the combined cooling effect of street canyon geometry and the surrounding built environmentEnvironmental Science and Pollution Research, 2024
- Ladybug Beetle Optimization algorithm: application for real-world problemsThe Journal of Supercomputing, 2022
- Multi-objective optimization of building design for life cycle cost and CO2 emissions: A case study of a low-energy residential building in a severe cold climateBuilding Simulation, 2021
- Impacts of urban morphology on reducing cooling load and increasing ventilation potential in hot-arid climateApplied Energy, 2018