Optimization Method for Energy Saving of Rural Architectures in Hot Summer and Cold Winter Areas Based on Artificial...

Area of Science:

• Building Technology and Science
• Energy Conservation
• Artificial Intelligence in Architecture

Background:

• Rural architectural energy consumption is rising, posing environmental threats, especially in regions with extreme climates.
• Accurate energy consumption prediction is crucial for effective building energy conservation strategies.
• Existing methods may not adequately address the specific energy use patterns of rural buildings in challenging climate zones.

Purpose of the Study:

• To develop and validate a neural network model for predicting energy consumption in rural buildings.
• To address the unique energy consumption characteristics of rural architecture in hot summer and cold winter areas.
• To provide a tool for optimizing building energy efficiency designs.

Main Methods:

• Construction of a neural network model using a specific dataset.
• Random application of functions to training samples for model development.
• Simulation tests to compare predicted results with calculated and target simulation values.

Main Results:

• The neural network model demonstrated high predictive accuracy for rural building energy consumption.
• Relative error between predicted and actual values was less than 4%.
• Average relative error (mean) and root mean square error (RMSE) were controlled within 2%.

Conclusions:

• The proposed neural network method accurately evaluates building energy consumption.
• The model enables high-speed conversion from a generalized approach to specific building energy goals.
• This research offers significant value and research significance for improving rural architectural energy efficiency.