The technological assessment of green buildings using artificial neural networks

This study aims to construct a comprehensive evaluation model for efficiently assessing appropriate technologies within green buildings. Initially, an Internet of Things (IoT)-based environmental monitoring system is devised and implemented to collect real-time environmental parameters both inside and outside the building. To evaluate the technical suitability of green buildings, this study employs a multifaceted approach encompassing various criteria, including energy efficiency, environmental impact, economic benefits, user comfort, and sustainability. Specifically, it involves real-time monitoring of environmental parameters, analysis of energy consumption data, and indoor environmental quality indicators derived from user satisfaction surveys. Subsequently, a Multi-Layer Perceptron (MLP) is selected as a conventional artificial neural network (ANN) model, while a Long Short-Term Memory (LSTM) model is chosen as an advanced recurrent neural network model in the realm of deep learning. These models are utilized to process and explore the collected data and assess the technical suitability of green buildings. The dataset comprises physical quantities such as temperature, humidity, and light intensity, as well as economic indicators including energy efficiency and building operating costs. Furthermore, the assessment process considers the building's life cycle assessment and indoor environmental quality factors such as health, comfort, and safety. By incorporating these comprehensive criteria, a holistic evaluation of green building technologies is achieved, ensuring the selected technologies' suitability and effectiveness. The model prediction results demonstrate that the proposed hybrid evaluation model exhibits high accuracy and robust stability in predicting building environmental parameters. For instance, the Root Mean Square Error (RMSE) for temperature prediction is 1.2 °C, the Mean Absolute Error (MAE) is 0.9 °C, and the determination coefficient (R²) reaches 0.95. Similarly, for humidity prediction, the RMSE, MAE, and R² are 3.5 %, 2.8 %, and 0.88. Compared to the traditional MLP and LSTM models alone, the proposed hybrid model shows significant improvements in predicting building energy consumption, with approximately 15 % and 12 % reductions in RMSE and MAE, respectively, and an increase in R² values of approximately 7 percentage points. These findings indicate that by amalgamation of the IoT and ANNs, this study successfully establishes a comprehensive model for accurately assessing technologies suitable for green buildings. This approach offers a novel perspective and methodology for the design and evaluation of green buildings.