The transition toward sustainable construction practices has intensified the demand for intelligent and energy-efficient building components, particularly smart window technologies. While numerous innovations exist, the selection of the most optimal smart window solution is difficult due to the trade-offs among conflicting criteria such as energy performance, economic feasibility, environmental impact, and user comfort. This study proposes an integrated Fuzzy Multi-Criteria Decision-Making (FMCDM) framework for selecting smart window technologies. The methodology combines the Fuzzy Analytic Hierarchy Process (FAHP) to determine criterion weights and the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) to rank alternatives. Nine sustainability-related criteria across the environmental, economic, and social dimensions were evaluated using expert input. The results identify thermochromic smart windows as the optimal choice. This research contributes a structured, adaptable, and scalable FMCDM framework for sustainable technology selection, with broader applicability to green product design and decision-making in the construction and energy sectors.

In the context of the architecture and construction industries implementing environmentally friendly sustainable solutions, smart glass is also designed using sustainable materials and sustainable operations, contributing to environmental protection efforts. The application of smart glass in large buildings optimizes the buildings’ operation, helping to reduce reliance on air conditioners that consume large amounts of electricity and emit significant amounts of CO₂ into the environment. Additionally, smart glass enhances energy-saving efficiency by intelligently regulating the indoor temperature and natural lighting, thereby reducing overall energy consumption and operational costs. In this study, the authors propose a fuzzy multi-criteria decision-making (MCDM) model to evaluate and select optimal sustainable smart glass technology based on technical, environmental, economic, and social criteria. The model integrates the fuzzy analytic hierarchy process (FAHP) to calculate the weights of the criteria and the Interactive and Multi-criteria Decision-Making in Portuguese Model (TODIM) to rank different smart glass technology alternatives. The findings highlight the most suitable smart glass technology, offering significant benefits in reducing energy consumption while ensuring aesthetic appeal and durability. This study provides a comprehensive approach to integrating sustainability into smart glass design, contributing to the development of green and energy-efficient buildings.

This paper presents a novel, explainable, and weather-independent day-ahead load forecasting (DALF). The proposed methodology integrates calendar-based segmentation using Classification and Regression Trees (CART), hybrid modeling with Multiple Linear Regression (MLR) and Gaussian Process Regression (GPR), and post-hoc error correction via Generalized Least Squares with Autoregressive Residuals (GLSAR). To enhance interpretability, Shapley Additive exPlanations (SHAP) are employed to quantify the influence of lagged load features and calendar variables across segmented forecasts. The framework is evaluated on real-world half-hourly data from the Electricity Generating Authority of Thailand (EGAT), encompassing both regular and holiday-specific load profiles. Experimental results demonstrate that the MLR–GPR–GLSAR configuration achieves superior performance, with a Mean Absolute Percentage Error (MAPE) of 0.72% and an R² of 0.99, outperforming Generalized Additive Models (GAM), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LGB), Convolutional Long Short-Term Memory (CNN-LSTM), and Neural Hierarchical Interpolation for Time Series (NHITS), as baselines. The proposed framework offers a scalable and interpretable solution for utilities operating in data-sparse environments. These findings affirm the importance of residual autocorrelation correction and calendar-aware segmentation in advancing DALF accuracy and transparency.