Posts

Hybrid LSTM–Transformer Framework for Accurate Indoor Operative Temperature Prediction in HVAC-Controlled Buildings

Image
Accurate prediction of indoor operative temperature is essential for improving HVAC system performance, enhancing occupant comfort, and reducing energy consumption in buildings. Operative temperature represents the combined effect of air temperature and the mean radiant temperature of surrounding surfaces as experienced by occupants. In highly controlled environments such as sentry buildings, precise thermal forecasting enables more responsive and energy-efficient climate control strategies. This study proposes a hybrid deep learning framework to improve the accuracy and robustness of indoor operative temperature prediction. Concept of Operative Temperature and Its Role in Thermal Comfort Operative temperature is widely used as a key indicator of indoor thermal comfort because it integrates both air temperature and radiative heat exchange between occupants and surrounding surfaces. Traditional temperature prediction approaches often focus only on air temperature, overlooking the infl...

Comparative Performance of Thermotropic Glazing and Vertical Shading Devices in Office Building Envelopes

Image
Dynamic façade technologies have emerged as effective strategies for improving building energy efficiency while maintaining indoor environmental quality. Thermotropic (TT) glazing is a responsive glazing technology capable of modulating solar heat gain automatically in response to ambient temperature changes. This study investigates whether TT glazing can serve as an effective alternative to conventional external vertical shading devices by examining building energy consumption, daylighting performance, and thermal comfort in office spaces across multiple climatic conditions. Thermotropic Glazing as a Dynamic Solar Control Strategy Thermotropic glazing operates through temperature-responsive materials that adjust their optical properties when exposed to solar radiation and rising surface temperatures. As the glazing becomes less transparent at higher temperatures, solar heat gain is reduced without the need for mechanical control systems. This adaptive behavior allows the glazing to...

EPC-Based Clustering Framework for Representative Building Selection and Scalable Energy Simulation

Image
Identifying representative buildings is essential for scalable urban energy simulation and effective retrofit planning. However, continuous monitoring data are often unavailable, limiting data-driven classification approaches. This study presents a structured methodology for selecting representative buildings through clustering of Energy Performance Certificate (EPC) attributes. By grouping buildings based on certificate-based features and validating clusters against thermal performance indicators, the research establishes a generalizable framework for simulation targeting and policy support without reliance on long-term metering. Six-Phase Clustering Workflow and Internal Validation The proposed methodology follows a six-phase workflow, beginning with EPC attribute preparation and feature engineering. Three clustering techniques—K-Medoids, Agglomerative clustering, and Gaussian Mixture Model (GMM)—were implemented to group buildings based on similarity. Cluster quality was assessed...

Participatory Design Model for Loose Parts Play in Urban Spaces

Image
Participatory design approaches have increasingly been applied in playground development to better align urban play environments with children’s needs and expectations. Although previous studies highlight children’s strong interest in loose parts play, limited research has explored participatory processes specifically focused on designing loose parts themselves. Considering the cognitive, physical, social, and emotional benefits of loose parts play, this study introduces a structured participatory design model that actively involves children and architecture students in the co-creation of play elements for urban spaces. Theoretical Background: Benefits of Loose Parts Play Loose parts play supports creativity, problem-solving, collaboration, and self-expression by allowing children to manipulate flexible, open-ended materials. Unlike fixed playground equipment, loose parts encourage adaptive and imaginative engagement, fostering developmental growth across multiple domains. Integrati...

Climate-Sensitive Energy Performance Assessment of Bio-Based Building Envelopes

Image
Bio-based construction materials are increasingly promoted as sustainable alternatives capable of reducing the environmental footprint of buildings while enhancing energy efficiency. However, many comparative studies assess these materials against conventional wall systems of equal thickness, often neglecting the influence of thermal mass and climate-specific behavior at the whole-building scale. Due to their lightweight structure and limited thermal mass, bio-based systems may struggle to balance heating and cooling demands across different climates. This study evaluates the energy performance of hemp concrete, wood concrete, and straw-based wall systems, emphasizing the interaction between insulation, thermal inertia, and climate conditions. Methodological Framework and Co-Simulation Strategy A validated co-simulation methodology integrating TRNSYS and MATLAB was employed to assess whole-building energy performance. Two analytical scenarios were developed to isolate and evaluate key...

Stochastic Optimization Framework for Robust Building Performance Under Occupant Behavioral Uncertainty

Image
Optimizing building performance requires acknowledging the stochastic nature of occupant control behaviors, which significantly influence energy consumption, thermal comfort, and visual comfort outcomes. Traditional building performance models often rely on oversimplified behavioral assumptions and demand extensive computational time for stochastic simulations. This study proposes a novel optimization framework specifically designed to address uncertainty in occupant behavior while improving computational efficiency and solution robustness in building design optimization. Methodological Integration of Stochastic and Intelligent Optimization Techniques The proposed approach integrates Sample Average Approximation (SAA) with Monte Carlo simulations to obtain convergent mean performance estimates under uncertainty. To accelerate optimization, machine learning (ML) models are coupled with a Pareto-based Genetic Algorithm (GA), enabling rapid prediction of building performance metrics acr...

Comparative Thermal Performance of Advanced Insulation Materials and Hybrid Wall Systems in Cold-Climate Buildings

Image
Improving building envelope performance is a critical strategy for reducing heating energy demand and enhancing indoor thermal comfort in cold climates. This study evaluates the thermal effectiveness of four advanced insulation materials—phase change materials (PCM), aerogel, vacuum insulated panels (VIP), and autoclaved aerated concrete (AAC)—through dynamic energy simulations. Using 24 years of hourly climate data, five wall configurations were analyzed, including an uninsulated reference case. The research focuses on annual heating demand, surface temperature stability, thermal time lag, and comfort hours to determine how different material properties contribute to energy efficiency and occupant comfort. Methodological Framework and Simulation Approach The investigation employed dynamic building energy modeling using EnergyPlus, incorporating long-term hourly climate data to ensure robust performance assessment. PCM behavior was simulated through an enthalpy–temperature phase ch...