Data-driven models have been used to capture human-building interactions from measured data. However, correlation alone doesn't always explain why occupants act or how their actions alter indoor thermal dynamics. This study develops a causality-based model that represents window operation as a behaviour driven by indoor conditions and as an intervention modifying outdoor-indoor built environment. Using data from four residential households in Seoul, South Korea, a structural causal model (SCM) incorporating logistic regression for window-opening behaviour was compared with a correlation-based model. Although both models showed comparable goodness-of-fit, only the SCM separated thermal continuity from behaviour-dependent exchange and enabled counterfactual evaluation of window states. Household-specific window-opening thresholds ranged from 21.60 to 28.02 degrees C, and a counterfactual case indicated a 0.154 degrees C change under alternative behaviour. The SCM further distinguished epistemic uncertainty from behaviour-driven aleatoric uncertainty, which was greatest when window-opening probability approached 0.5, where occupant behaviour was most uncertain.
Building energy simulations have traditionally relied on historical weather files that do not account for climate change. This study presents an open-source, automated Python workflow to generate future hourly weather files compatible with EnergyPlus for building energy and renewable energy simulations across North America through 2100. The methodology combines quality-controlled historical data (CWEEDS, GHCNh, NSRDB) with bias-corrected NA-CORDEX projections using Quantile Delta Mapping and analogue-based temporal disaggregation. A machine learning step is introduced to decompose solar radiation for EPW compliance. The pipeline produces ready-to-use CSV and EPW files, enabling direct assessment of hourly building performance and renewable energy potential under future climate scenarios. Validation indicates plausible warming (e.g. +3 degrees C-6 degrees C in Winnipeg under RCP8.5) and consistent photovoltaic simulation results. The open-source Python code is made publicly available.
With the advancement of occupant-centric control research, adjusting indoor environmental parameters based on individual thermal preferences has become increasingly important. However, the diversity of individual thermal responses and complex interactions among influencing variables make accurate modelling challenging. To address these issues, this study proposes a data-efficient logistic regression model designed to overcome the limitations of conventional data-driven approaches that rely on large and balanced datasets. In this context, 'data-efficiency' refers to the model's ability to maintain reliable predictive performance even when trained with a limited number of data samples. The proposed model achieved accuracies of 64.0% and 80.4% when trained on 10 and 80 data points, respectively. The proposed approach offers a practical and interpretable framework for occupant-centric indoor environmental control systems, reducing data collection requirements while maintaining prediction reliability.
Accurately modelling occupant behaviour is essential for realistic building performance simulations, yet both the temporal and spatial behaviour diversity remain poorly monitored and modelled. This study develops practical methodologies and guidelines to determine the minimum monitoring duration, the number of rooms per dwelling, and the number of rooms required to develop representative occupant behaviour models. The approach was applied to a dataset of 76 French dwellings monitored for window opening behaviour during summer. Methodological advances in modelling include the use of sine and cosine transformations for time-of-day effects and a multivariate normal distribution to model occupant behaviour spatial diversity and to keep the linear correlations between opening and closing models. Results indicate that two months of monitoring, while instrumenting all rooms is necessary to represent occupant behaviour diversity. Capturing population-level diversity requires monitoring several hundred dwellings, exceeding the scope of most existing campaigns.
Ceiling fans can improve thermal comfort while reducing building energy consumption, yet the transient airflow and turbulence they generate remain insufficiently understood. This study develops and validates a three-dimensional transient Computational Fluid Dynamics (CFD) model to investigate fan-induced airflow. Experimental measurements from literature paper in a controlled chamber were used for validation. Three moving mesh approaches (Dynamic Remeshing, Sliding Mesh, and Overset Mesh) and four turbulence models (Standard $ k-& varepsilon;, RNG -& varepsilon;, SST k- k-omega, and Transition k-kl-omega) were evaluated in terms of accuracy and computational efficiency. Results show that airflow velocity and turbulence intensity exhibit periodic fluctuations associated with blade-passing frequency, which diminish with distance from the fan. Both Overset Mesh and Dynamic Remeshing reproduced measured flow fields accurately, while the Overset approach achieved comparable accuracy with 2.5 times lower computational cost. Among the turbulence models tested, SST k-omega provided the most consistent agreement with experimental data. The findings provide practical guidance for efficient and reliable CFD modelling of fan-assisted indoor airflow.
This work introduces a method for the estimation of fluctuating air change rates (ACR) in occupied buildings, using measurements of CO $ _2 $ 2 concentration. The target of a measurement-based method is to propose an alternative to airflow network simulation, which relies on many assumptions and uncertain parameters to calculate air change rates. The methodology is based on the stochastic formulation of the CO $ _2 $ 2 conservation equation, solved by the Extended Kalman Filter. It allows accounting for measurement noise, modelling uncertainty and input uncertainty, in the evaluation of the ACR. Two improvements to the base CO $ _2 $ 2 conservation inverse problem, to account for eventual high fluctuations of the ACR: the state-space model is augmented with an equation for the CO $ _2 $ 2 production rate, and the variance of the ACR may depend on the detection of window openings. The case study is a monitored experimental test house, which was also simulated in EnergyPlus, so that the method could be tested on simulated data or real measured data. Results show that the estimated ACR may be in good agreement with values calculated by airflow network simulation, under some conditions: the difference between indoor and outdoor CO $ _2 $ 2 concentration cannot be too small for ACR to be identifiable. Very high air change rates are therefore difficult to estimate, beyond a few minutes after a window is opened. The method can however be considered promising for establishing the air flow signature of monitored buildings and designing natural cooling solutions.Highlights
High-density residential buildings pose unique challenges for safe evacuation under fire emergencies due to complex spatial layouts, population clustering, and rapid hazard progression. This study develops an integrated simulation framework that couples fire dynamics with agent-based modelling to evaluate evacuation performance and occupant safety under varied conditions. Engineering-informed behavioural logic, hazard thresholds, and spatial constraints are embedded to simulate realistic, time-sensitive scenarios. The framework is validated using real fire cases from Hong Kong public housing and applied across 80 diverse scenarios varying in layout, fire origin, and response delays. Results show that distributed exits reduce the number of at-risk occupants by over one-third when delays exceed 60 s, while premature evacuation may lead to greater risk exposure due to blocked corridors. By correlating dynamic fire hazard progression with occupant evacuation and predicting specific survival windows for trapped occupants, the proposed framework facilitates entrapment-aware rescue planning during residential building fires.
A smart building HVAC control competition crowdsourced and compared algorithms on fair and equal ground using the standardized BOPTEST framework. The competition attracted 138 participants, but only 9% submitted valid solutions for the final stage, highlighting the complexity of advanced HVAC control design. The winning solutions showed significant potential to reduce energy use and cost by shifting demand, without compromising occupant comfort. Across scenarios, thermal energy cost reductions of 36-76% relative to a baseline, were achieved. In peak heat periods, the cost reduction leveraged limited energy use reduction (0-15%), but more significant energy price reduction (34-62%). This shows smart controls' ability to avoid as much as possible consumption during the morning peak hours, when spot prices are tendentially the highest. Hosting the competition has highlighted challenges in creating competitions that both are fair and promotes solutions that are transferable to real life implementation.
Traditional building energy modelling workflows remain labor-intensive and error-prone, requiring specialized expertise that limits broader adoption. This paper introduces a novel Model Context Protocol (MCP)-enabled framework that connects AI assistants to EnergyPlus through MCP, a standardized interface for tool invocation and context management. Two complementary integration paradigms are presented and compared: conversational integration, where users interact through natural language while an AI assistant orchestrates MCP tools on demand, and agentic workflow integration, where specialized agents coordinate autonomously to complete multi-step tasks. Using an experimental testbed for residential buildings, the end-to-end workflows are demonstrated. The conversational approach reduced typical inspection and modification tasks from 1-2 h to under 15 min, while maintaining full transparency through visible tool invocations. The agentic approach automated parametric analysis. These demonstrations establish MCP as a foundational layer for AI-assisted building energy modelling, enabling natural language interactions with simulation tools while preserving professional oversight and decision-making authority.Highlights An MCP-enabled framework provides standardized integration between AI assistants and EnergyPlus for building energy modelling workflows.Two complementary paradigms are demonstrated: conversational integration for exploratory tasks and agentic workflow integration for systematic automation.End-to-end demonstrations on a residential energy model show an 80% to 90% time reduction for model inspection, modification, and analysis tasks.The framework augments rather than replaces professional judgment, with AI handling tool orchestration while practitioners retain decision-making authority.The approach establishes a foundational infrastructure for advanced capabilities including parametric simulations, BIM-to-BEM translation, and automated model calibration.
Model Predictive Control (MPC) in building energy management requires transient thermal models balancing thermodynamic accuracy with computational efficiency. Standard spatial discretization triggers state-space inflation, paralyzing real-time solvers, while Transfer Matrix Methods (TMM) suffer from high-frequency numerical overflow and assume material homogeneity. This paper introduces a novel frequency-domain framework based on the continuous spatial Riccati equation. A recursive admittance mapping strictly bounds exponential growth, preventing numerical instability. The primary contribution of this work is extending this linear propagator via regular perturbation theory to analytically resolve spatial property gradients ( $ \lambda (x) $ lambda(x)) and non-linear $ T<^>4 $ T4 radiative boundaries as equivalent harmonic source terms. This meshless approach eliminates spatial truncation errors. It corrects peak heating load deviations of 21.9% in wetted media and mitigates artificial nocturnal cooling fluxes of 12.0 W/m $ <^>2 $ 2. Preserving $ \mathcal {O}(N) $ O(N) spatial complexity, the framework avoids state-space inflation, ensuring high-speed execution for multi-week MPC optimization.
Accurate short-term building energy consumption forecasting is crucial for the intelligent operation of Building Energy Management Systems (BEMS), but it is challenging due to strong nonlinearity, weather uncertainty, and occupancy variability, as well as the sensitivity of Long Short-Term Memory (LSTM) models to hyperparameter settings. This study proposes an ICPO-LSTM framework, in which an Improved Crested Porcupine Optimizer (ICPO) is developed to efficiently optimize multiple LSTM hyperparameters. ICPO incorporates Cat chaotic mapping initialization, nonlinear dynamic regulation, and adaptive T-distribution perturbation to enhance convergence stability and global search ability. The proposed method is evaluated using two heterogeneous datasets, including an Internet of Things (IoT)-based high-rise office building in Xi'an, China, and a public library building from the Building Data Genome 2 (BDG2) dataset. Experimental results demonstrate that ICPO-LSTM consistently outperforms other optimization-based LSTM models and advanced deep learning methods, while achieving a favourable trade-off between prediction accuracy and computational efficiency.
The integration of ceiling fans with radiant systems remains underexplored despite their potential to address cooling capacity limitations. This study adopts a two-step approach to quantify the impact of elevated air movement on thermally activated building systems (TABS). First, we used OpenFOAM to calculate convective heat transfer coefficients under varying airflows, air-to-surface temperature differences, and zone sizes. These coefficients also apply to ceiling fans in buildings without radiant systems. Second, we implemented these coefficients in EnergyPlus to evaluate key radiant design parameters. Scenario 1 results show median steady-state cooling heat transfer rates increase of up to 47% relative to the no-fan cases when operative temperature is held constant. Scenario 2 demonstrates a median cooling effect of up to 4.8 K under fixed capacity, reflecting both lower zone temperatures and direct air movement on occupants. Overall, TABS-fans systems offer a scalable strategy to enhance comfort, increase capacity, and reduce energy demand.Highlights
This study investigates how uncertainty in occupancy sensor performance propagates through residential smart-thermostat control and shapes energy savings, thermal comfort, and peak demand. A four-step framework was used. First, stochastic models of occupancy schedules and sensor accuracy were calibrated using long-term field data from a single-family home in Texas. Second, these models were embedded in an EnergyPlus simulation platform via PyEMS to dynamically couple occupant behaviour, sensing errors, and building physics. Third, over ten thousand Monte Carlo simulations were conducted on an HPC cluster across seven IECC climate zones, varying setpoints, occupancy patterns, and sensor sensitivity. Fourth, standardized metrics were used to quantify energy, comfort, and demand impacts. Results show that sensor uncertainty substantially widens the performance range of smart thermostats. High sensor accuracy does not guarantee optimal outcomes, as false-positive and false-negative errors propagate nonlinearly through HVAC operation. Moderate sensitivity levels (0.4-0.7) best balance energy efficiency and comfort.
Rising temperatures and urban heat islands (UHI) affect human health and well-being. Green infrastructures (GI) can mitigate UHI and reduce indoor building temperatures through shading (lower solar gains) and evapotranspiration. However, quantifying these effects is challenging, as most building performance simulation (BPS) tools accurately model conventional cooling but lack greenery effects. Therefore, we developed facade greening parameters in IDA ICE using ENVI-met outdoor microclimate simulations that include ecosystem services from greenery. A case study in Vienna, Austria, assessed renovated and unrenovated buildings under future climate scenarios (RCP4.5 and RCP8.5). Cooling effects in IDA ICE were negligible in renovated buildings and up to 1.1 degrees C in unrenovated ones. The study demonstrates that modelling facade greening in IDA ICE is feasible, though fully capturing GI's benefits requires further BPS tool development.
