According to the China Building Energy Consumption and Carbon Emissions Research Report (2023), the construction industry accounts for 36.3% of total societal energy consumption, with residential buildings contributing significantly due to their extensive coverage and high operational frequency. Addressing energy efficiency and carbon reduction in this sector is critical for achieving national sustainability goals. This study proposes an optimization methodology for rural dwellings in Inner Mongolia, focusing on reducing energy demand while enhancing indoor thermal comfort and daylight performance. A parametric model was developed using Grasshopper, with energy consumption, thermal comfort (PPD), and Useful Daylight Illuminance (UDI) simulated through Ladybug and Honeybee tools. Key parameters analyzed include building morphology, envelope structures, and indoor thermal environments, followed by systematic optimization of building components. To refine multi-objective inputs, a specialized wall database was established, enabling categorization and dynamic visualization of material properties and construction methods. Comparative analysis demonstrated a 22.56% reduction in energy consumption, 19.26% decrease in occupant thermal dissatisfaction (PPD), and 25.44% improvement in UDI values post-optimization. The proposed framework provides a scientifically validated approach for improving energy efficiency and environmental adaptability in cold-climate rural architecture.
Energy consumption accounts for a significant proportion of China’s building operations, exhibiting notable regional variations influenced by geographic characteristics. Factors affecting building energy consumption during transitional seasons are particularly complex in severely cold regions. This study selected a university library in Hohhot, Inner Mongolia Autonomous Region, as its research subject, employing a hybrid TCN–transformer model to conduct predictive experiments on short-term building energy consumption. We first collected environmental data from Hohhot’s spring–summer transitional period. Following parameter screening and preprocessing, this dataset was input into the TCN–transformer model. By integrating TCN with transformer’s self-attention mechanism, the model addresses the region’s high noise levels and non-stationarity, enabling precise forecasting. To validate the effectiveness of the proposed model, a comparative analysis was conducted against traditional models, namely SVR and LSTM, on the same dataset. The results demonstrated that TCN–transformer achieves superior comprehensive performance, evidenced by a higher prediction accuracy (R2 = 0.8765) and lower error (MAE = 0.24603, RMSE = 0.32829), outperforming the baseline models. This research provides an innovative and efficient hybrid modelling approach and technical methodology for predicting building energy consumption during transitional seasons in severely cold regions, holding positive implications for enhancing building energy efficiency and promoting sustainable development.