Parametric Building Models Enhance High-Rise Office Performance by 50%

Why It Matters

This research demonstrates the power of creating generalized, data-driven models for complex building typologies. By moving beyond single-case studies, designers can leverage these frameworks to explore a wider range of design possibilities and achieve optimized performance outcomes early in the design process.

Key Finding

The study successfully created reusable parametric models for high-rise offices, improved prediction accuracy using ensemble learning, identified key design drivers, and achieved substantial reductions in energy use and increases in daylighting comfort through multi-objective optimization.

Key Findings

• Parametric prototype models establish clear parameter ranges for geometry, envelope design, and thermal performance, offering reusable models and data.
• Stacking ensemble models significantly outperform individual models in predicting building performance.
• Space length, aspect ratio, usable area ratio, window U-value, and solar heat gain coefficient are primary drivers of building performance.
• Optimized solutions reduced energy use by 3.79–11.81% and enhanced daylighting comfort by 40.16–50.32% while maintaining thermal comfort.

Research Evidence

Aim: To develop a framework for multi-objective optimization of high-rise office buildings using parametric prototype models and advanced simulation techniques to improve energy efficiency, daylighting, and thermal comfort.

Method: Simulation and Optimization

Procedure: Parametric prototype building models were developed based on real-world projects. Building performance was simulated using Grasshopper and Honeybee to generate large datasets. Stacking ensemble learning models were used as surrogate predictors for energy use, daylighting, and thermal comfort. Multi-objective optimization was performed using the NSGA-III algorithm.

Context: High-rise office building design in urban environments.

Design Principle

Leverage parametric modelling and data-driven simulation for systematic, multi-objective optimization of building designs.

How to Apply

When designing high-rise buildings, create a set of parametric models representing common typologies. Use simulation software to generate performance data across a range of design variables, then employ machine learning and optimization algorithms to identify optimal solutions.

Limitations

The prototype models are based on specific design practices in Shandong, China, and may require adaptation for different geographical or regulatory contexts. The study focuses on specific performance metrics and may not encompass all relevant design considerations.

Student Guide (IB Design Technology)

Simple Explanation: By creating flexible computer models of buildings that can be easily changed, researchers found ways to make tall office buildings use less energy and have better natural light, improving comfort for people inside.

Why This Matters: This research shows how advanced modelling and optimization techniques can lead to tangible improvements in building performance, offering a data-driven approach to sustainable design.

Critical Thinking: How might the identified key performance drivers vary for different building typologies (e.g., residential vs. commercial) or climatic zones?

IA-Ready Paragraph: This research by Zhang and Zhuang (2025) provides a robust methodology for optimizing high-rise office building designs through parametric modelling and multi-objective optimization. Their work demonstrates that by developing generalized prototype models and utilizing advanced simulation and ensemble learning techniques, significant improvements in energy efficiency and daylighting can be achieved, offering a data-driven approach that can inform early-stage design decisions and lead to more sustainable and comfortable built environments.

Project Tips

• When defining your building's parameters, ensure they reflect realistic design choices and constraints.
• Consider using a combination of simulation tools and data analysis techniques to evaluate performance.
• Clearly document the range of parameters explored and the optimization objectives.

How to Use in IA

• Reference this study when discussing the use of parametric modelling for performance optimization in your design project.
• Use the identified key performance drivers as a basis for your own design investigations.

Examiner Tips

• Ensure your parametric models are well-defined and the parameter ranges are justified.
• Clearly articulate the optimization objectives and the methods used to achieve them.

Independent Variable: ["Geometric parameters (space length, aspect ratio, usable area ratio)","Envelope design parameters (window U-value, SHGC)"]

Dependent Variable: ["Energy use","Daylighting performance","Thermal comfort"]

Controlled Variables: ["Building typology (high-rise office)","Location (Shandong, China)","Simulation software used"]

Strengths

• Development of reusable parametric models.
• Application of advanced ensemble learning for improved prediction accuracy.
• Comprehensive multi-objective optimization approach.

Critical Questions

• To what extent can the findings be generalized to other building types or climates?
• What are the computational costs associated with this modelling and optimization approach?

Extended Essay Application

• Investigate the impact of different façade designs on the energy performance and daylighting of a specific building type using parametric modelling.
• Explore the use of machine learning to predict user comfort based on environmental parameters in a designed space.

Source

Multi-Objective Optimization Design Based on Prototype High-Rise Office Buildings: A Case Study in Shandong, China · Buildings · 2025 · 10.3390/buildings15173071