Machine learning algorithms provide valuable data support for designing and optimizing low-carbon residential buildings. However, when used directly for carbon emission prediction and analysis, these models often lack proper parameter tuning and optimization. The different impacts of various independent variable datasets on predictive performance also remain to be clarified. In China's cold zones, where residential buildings share similar architectural structures, energy-saving designs, and spatial layouts, carbon emissions primarily come from the operational phase and the production stages of building materials, with heating emissions being a significant component. This study aims to elucidate the effectiveness of different machine learning algorithm models in guiding low-carbon residential design in these cold zones, offering architects criteria for selecting proper algorithms. This study focuses on automatic parameter tuning and optimization for several commonly used algorithms in the context of low-carbon design of buildings, including multiple linear regression, classification and regression tree, random forest, adaptive boosting, gradient boosting regression tree, and multilayer perceptron. The study compares and analyzes the performance limits and applicability of these algorithms and independent variable datasets in predicting carbon emissions during building material production and heating stages.

This paper elaborates on the target boundaries, parameter ranges, optimization processes, and validation methods for optimizing machine learning algorithm models. Through comprehensive research and simulation analysis of 37 reinforced concrete shear wall residential buildings and their derivative schemes in cold zones, multiple independent variable datasets suitable for establishing predictive models are identified. Cross-validation and grid search techniques are employed to optimize the predictive performance limits of different machine learning algorithms and independent variable datasets. Subsequently, 120 models for predicting carbon emissions from building materials and 60 models for transforming steady-state heating consumption into dynamic heating consumption using the six mentioned algorithms are established.

A horizontal comparison of the models reveals that algorithms such as multiple linear regression, random forest, and gradient boosting regression trees exhibit relatively good performance (R² over 0.900) in carbon emission prediction after hyperparameter tuning across different independent variable datasets. Random forest and gradient boosting regression tree models excel in error control and offer similar predictive accuracy to multiple linear regression but lack interpretability. In contrast, multiple linear regression models provide clearer equations and stronger guidance for low-carbon design and optimization, focusing on carbon emission reduction during building material production or winter heating stages. Models based on the total residential building area exhibit optimal performance in predicting building material carbon emissions. Predictive models built on parameters such as the number of above-ground and underground floors, building width and depth, total household numbers, number of bedrooms for standard floor, and total number of residential bathrooms in the residence also demonstrate strong predictive capabilities for building material carbon emissions. For predicting the conversion coefficient during the heating stage, including the number of households and bedrooms per standard floor as independent variables significantly enhances predictive performance.

Although various machine learning models are useful for predicting residential building carbon emissions, the multiple linear regression model stands out owing to its excellent predictive performance and its intuitive representation of how design parameters affect carbon emissions. By utilizing different and appropriate independent variable datasets, such as the total number of floors, floor height, building dimensions, number of households and bedrooms on a floor, and corrected coefficients for urban meteorological parameters (including outdoor average temperature during the heating season, actual heating days, and roof and wall heat transfer coefficients), or by adopting the finally determined total building area, the multiple linear regression algorithm can deliver timely and multi-faceted guidance. These results are crucial for low-carbon design and optimization during the primary stages of the residential lifecycle in China's cold zones.

Existing design standards for energy efficiency impose rigorous static restrictions on the shape coefficient and envelope performance of buildings. However, these requirements are incompatible with dynamic adjustment to real-time changes in the weather. Thus, the loss of energy-saving effect and indoor use quality of the building proffers the potential for improvement. Therefore, this study introduces the south-oriented combined external window design for buildings based on the principle of leap heat transfer. This design improves the solar heat gain during the daytime and the insulation performance at night, which is a feasible strategy to dynamically improve the indoor thermal environment and reduce the building load. However, the effect of this design strategy on the Tibetan plateau region still needs further investigation. To improve the energy efficiency and indoor usage quality of office buildings, this study takes a typical office building in Xigaze as the object to explore the more suitable design strategies for south-oriented external windows.

This study compares nine building cases with distinct south-oriented external window designs. By quantifying the differences in building performance induced by each window design, the most efficient south-oriented external window design in the Tibetan plateau region is identified. The triple-glazing low-E windows in the baseline case meet the thermal performance requirements. In the rest of the design cases, the external window components consist of a 6 mm glass curtain wall with heat-break bridge aluminum alloy, a normal insulating window or low-E insulating window composed of two pieces of 6 mm glass and 12 mm air interlayer, and an insulating cotton curtain. DesignBuilder 6.1 is used in this study to analyze the cool and heat loads, hourly operating temperature, and thermal comfort of the primary rooms in a dynamic simulation throughout the year. Consequently, the comparison of the performance scores of nine building cases serves as the foundation for case validation.

The results indicate the followings: (1) In the absence of heating and air conditioning, the indoor operating temperature fluctuates less in summer and more in winter. (2) In the absence of heating and air conditioning, the average time percentage of indoor temperature (from 18 ℃ to 26 ℃) varies significantly depending on various types of windows. The dynamically adjustable external window allows for a longer period of comfort in the office and a relatively long period of comfort in the dormitory. (3) The combination of a 6 mm glass curtain wall with heat-break aluminum alloy, normal insulated windows consisting of two pieces of 6 mm glass and 12 mm air interlayer, and thermal insulation curtains presents the lowest heat load and total load in the design case. (4) Compared with the baseline case, the proposed external window design enables a higher level of annual thermal satisfaction and indoor thermal sensation.

For office buildings in the frigid plateau region, glass curtain walls and heat-collecting walls should be used to fully capture solar radiation during the daytime. Meanwhile, thermal insulation should be employed to reduce heat dissipation at night. The proposed external window design presents the most significant effect on reducing building load and improving thermal comfort. Moreover, compared with windows employing low-E glass, this design reduces the construction cost and can be considered a more efficient choice for the south-oriented external window design of office buildings in the frigid plateau region.