AI for building energy modeling: A transformation

There is increasing need to apply building information modeling (BIM) to low energy buildings, this includes building energy modeling (BEM). If a building energy model can be flawlessly generated from a BIM model, the energy simulation process can be better integrated within the design, can be more competent, and timesaving. However, concerns about both the reliability and integrity of the data transfer process and the interoperability between the BIM and BEM prevent any implementation of BIM-based energy modeling on a large scale. This study addresses the accuracy and integrity of BIM-based energy modeling by investigating how well Autodesk's Revit (BIM), in conjunction with two of the most used energy modeling programs (BEM) known as DesignBuilder and Virtual Environment (IES-ve), were integrated in terms of interoperability, including location and weather files, geometry, construction and materials, thermal zones, occupancy operating schedules, and HVAC systems. All misrepresented data during the interoperability process were identified, followed by benchmarking between the BIM-based energy modeling simulation outcomes and the actual energy consumption of the case study, to assess the reliability of the process. The investigation has revealed a number of interoperability issues regarding the BIM data input and BEM data interpretation. Overall, BIM-based energy modeling proved to be a promising tool for sustainable and low energy building design, however, the BIM to BEM process is a non-standardized method of producing building energy models as it varies from one modeler to another, and the BIM to BEM process. All these might slow down any possible application for the process and might cause some uncertainties for the professionals in the field applying it.

The availability of large-area sensing, scalable algorithms, and high-performance computing has enabled the possibility of urban-scale building energy modeling using new methods not limited to the scalability of manual building energy model creation or retrieval of county-by-county tax assessor's data. Automatic Building detection and Energy Model creation (AutoBEM) has created 178,368 building energy models for the Electric Power Board (EPB) of Chattanooga, TN, and compared simulation performance to 15-minute data from each building. These models leverage several data sources (e.g. imagery, GIS, utility), software tools to extract building properties (e.g. footprint, height, facade type, window-to-wall ratio, occupancy, building type), simulate at scale on two of the world's #1 fastest supercomputers, and provide web-based visual analytics. Grid-interactive efficient buildings offer the potential to reduce utility and rate-payer energy costs during each calendar month's hour of critical generation -- when the least efficient, most costly, and often dirtiest generation assets must be brought online. In this paper, EnergyPlus is used to simulate over 150,000 buildings to assess the technical potential of utility-controlled smart thermostats. This is analyzed under a couple scenarios leveraging buildings as thermal batteries via pre-conditioning to coast through peak hours. Results are provided in box and whisker plots assessing the distribution of peak demand reduction at the utility-scale along with breakouts of energy and demand savings by building type and vintage.

This research investigates the integration of building energy modeling (BEM) within collaborative construction projects to inform design decisions for achieving high-energy performance goals. The study aims to understand current practices, benefits, and challenges associated with this integration. Using an ethnographic case study approach focused on two high-energy performance social housing projects with integrated project delivery and integrated design processes, data were collected through direct observations, document analysis, and interviews with project team members. Design process modeling was utilized to dissect current practices, followed by a hybrid inductive and deductive thematic analysis to find challenges related to energy performance design in collaborative projects. Findings from this research revealed that BEM experts often operate in isolation, with late integration of energy models into design decisions. Compliance-centric BEM usage and challenges related to interoperability of design and BEM tools further compound the issue of seamless collaboration. However, the study highlights that early collaboration among project stakeholders emerges as a pivotal factor in informed design decisions, bridging the gap between energy modeling and design. This research provides valuable insights for practitioners seeking to optimize BEM in their design process, and offers support to policymakers aiming to enhance the role of BEM in projects.

Building and Urban-Scale Energy Modeling: A Comparative Literature Review of Building Energy Modeling (BEM) and Urban Building Energy Modeling (UBEM)

Synthetic 3D Building Energy Model (BEM) Dataset Generation for Human + AI Synergies in Early-Phase High Performance Building Design

Building energy models are largely comparative in nature, from early design phase to final energy code compliance models. While there is merit in a comparative framework, with the advent of empirical compliance targets, improving the efficacy of building energy models is imperative to better align model results with future building energy consumption. To refine this alignment, even early design phase energy models should undergo proper quality checking to improve the reliability of comparative studies and yield design strategy results that will hold true in later design phases and in future building energy consumption. Subject to time or user expertise, many early design phase energy models forgo proper quality checking, which can lead to misaligned expectations when the intent for a building owner is to ultimately meet empirical compliance targets. This paper outlines an automated approach to help energy modelers efficiently quality check early design phase energy models and minimize discrepancies between comparative modeling and empirically based performance targets. The test cases presented in this paper demonstrate how quality checking improves the reliability of early comparative studies.

Building energy models are largely comparative in nature, from early design phase to final energy code compliance models. While there is merit in a comparative framework, with the advent of empirical compliance targets, improving the efficacy of building energy models is imperative to better align model results with future building energy consumption. To refine this alignment, even early design phase energy models should undergo proper quality checking to improve the reliability of comparative studies and yield design strategy results that will hold true in later design phases and in future building energy consumption. Subject to time or user expertise, many early design phase energy models forgo proper quality checking, which can lead to misaligned expectations when the intent for a building owner is to ultimately meet empirical compliance targets. This paper outlines an automated approach to help energy modelers efficiently quality check early design phase energy models and minimize discrepancies between comparative modeling and empirically based performance targets. The test cases presented in this paper demonstrate how quality checking improves the reliability of early comparative studies.

With increasing awareness of the contribution of buildings to global warming, the construction industry has begun to be more responsive to energy-efficient buildings. The emergence of building information modeling (BIM) with building energy modeling (BEM) provides industry with means to address related issues through integrated energy analysis of buildings. Nevertheless, connecting BIM technology to BEM includes issues of information exchange among the participants in the process. While the prevailing view in the literature is that there is a need to redefine the process, it is suggested that beyond that the success of BEM includes stakeholder management, which can be implemented through BIM’s social capabilities. Therefore, in order to address the integration issues between them, this study proposes a social concept for connecting BIM to BEM, which is reflected in the model for implementation of corporate social responsibility (CSR) through BIM for BEM (CSR–BIM–BEM model). The examination of the relevance of BIM’s social capabilities to the BEM process according to this model was conducted on three levels. First, the implications of integrating BIM technology into the BEM process were examined through expert interviews, and the need for social perception became apparent. Second, the examination of the model’s criteria by the experts supported its ability to promote the BEM process. Third, an examination of two case studies proved, using social network analysis and participant interviews, the model’s feasibility, in terms of BEM process parameters. A direct link was found between BIM’s management centrality, reflected in BIM involvement in stakeholder management, and progress in the BEM process. These results illustrate the importance of BIM’s social role in building energy modeling.

Comparative energy performance evaluation and uncertainty analysis of two building archetype development methodologies: A case study of high-rise residential buildings in Qatar

Current building energy modeling (BEM) tools lack the capability to inherently simulate the impacts of urban microclimates on building energy performance. While efforts have been made to integrate BEM with Urban Microclimate Modeling (UMM) tools, their ability to capture spatial and seasonal microclimate variations remains limited. This review critically evaluates existing urban microclimate-integrated BEM approaches and their effectiveness in modeling the complex interactions between urban form, microclimate, and building energy performance. Through an analysis of 94 research articles, the review first examines the influence of urban form on microclimates, followed by an assessment of how microclimatic conditions impact building energy use. Additionally, it evaluates conventional modeling frameworks employed in BEM tools and their limitations in representing dynamic microclimatic variations. The findings emphasize the non-linear heat exchange relationships between urban form and microclimate, typically modeled using computationally intensive Computational Fluid Dynamics (CFD)-based UMM tools. This review introduces a classification of heat exchange types: atmospheric heat exchange, involving air temperature, wind, and humidity, and non-atmospheric heat exchange, driven by radiative interactions with surrounding urban surfaces. The study further highlights that modifying standard weather files and heat transfer coefficients alone is insufficient for BEM tools to accurately capture near-surface microclimate variations. By identifying critical insights and research gaps, this review establishes a foundation for advancing next-generation urban microclimate-integrated BEM approaches, emphasizing the need for computationally efficient and dynamically responsive modeling techniques.

The heating, ventilation, and air conditioning (HVAC) system is one of the most complex parts in a building design, which requires a high level of specialty to interpret and analyze during building energy modeling. From an energy simulation perspective, significant efforts are required in extracting HVAC information from the two-dimensional (2D) mechanical drawings or three-dimensional (3D) design models and manually inputting the data into the energy models. This tedious, error-prone, and time-consuming process has hindered high productivity in energy analysis. Automatically transforming HVAC data already contained in building information modeling (BIM) into building energy modeling (BEM) can significantly accelerate this process and improve efficiency during design iterations. To automate this process, the authors proposed a new algorithmic method by leveraging the state-of-the-art data-driven reverse engineering algorithm development (D-READ) method and the invariant signatures of HVAC objects. Following the proposed method, an algorithm was developed using a 2-story residential building model and a 2-story office building model. It successfully transformed HVAC data from BIM to EnergyPlus input file following the Industry Foundation Classes (IFC) standard. It was tested on two testing models with different HVAC systems [i.e., a 4-story office building model with a boiler radiator system and a 2-story clinic building with a variable air volume (VAV) system], which achieved 97.5% and 98.7% transformation accuracy compared with evaluation models manually created in commercially available software, respectively. Results also showed a satisfactory precision (<9.6% error) in total energy consumption by the algorithmically generated model when compared with the evaluation model. This work provides a new IFC-based approach to address the research gap of HVAC interoperability between BIM and BEM and supports better accessibility compared with a proprietary workflow. It builds a solid step for realizing seamless and fully-automated HVAC information transformation between BIM and BEM, for complete BIM-BEM interoperability.

Traditional energy modeling methods are usually time-consuming and labour-intensive, so energy simulation is rarely performed early in building design. If a Building Energy Model (BEM) can be seamlessly generated from a Building Information Modeling (BIM) model, the energy simulation process can be much more efficient and better integrated in design. The concerns about BIM to BEM data transfer integrity and the reliability of simulation results are preventing wider adoption of BIM-based energy simulation. This study aimed to address these two obstacles and increase energy modelers’ confidence in using BIM for energy analysis. Green Building Studio (GBS) was used to simulate energy use and generate eQuest and EnergyPlus input files. Two building types were modeled in Revit with various iterations and BEM input files downloaded from GBS were compared line by line to identify and classify discrepancies. Simulation results from BIM-based and traditional modeling were compared to test reliability and showed unexpectedly good agreement across methods.

Traditional energy modeling methods are usually time-consuming and labour-intensive, so energy simulation is rarely performed early in building design. If a Building Energy Model (BEM) can be seamlessly generated from a Building Information Modeling (BIM) model, the energy simulation process can be much more efficient and better integrated in design. The concerns about BIM to BEM data transfer integrity and the reliability of simulation results are preventing wider adoption of BIM-based energy simulation. This study aimed to address these two obstacles and increase energy modelers’ confidence in using BIM for energy analysis. Green Building Studio (GBS) was used to simulate energy use and generate eQuest and EnergyPlus input files. Two building types were modeled in Revit with various iterations and BEM input files downloaded from GBS were compared line by line to identify and classify discrepancies. Simulation results from BIM-based and traditional modeling were compared to test reliability and showed unexpectedly good agreement across methods.

Building performance simulation can be used for retrofit analysis. However, it is time-consuming to create building energy models for existing buildings. This paper presented and implemented a rapid building energy modeling method for existing buildings by using prototype models and automatic model calibration for retrofit analysis with uncertainty. A shopping mall building located in Changsha, China, was selected as a case study to demonstrate the rapid modeling method. First, a toolkit named AutoBPS-Param was developed to generate building energy models with parameterized geometry data. A baseline EnergyPlus model was generated based on the building’s basic information, including vintage, climate zone, total floor area, and percentage of each function type. Next, Monte Carlo sampling was applied to generate 1000 combinations for fourteen parameters. One thousand EnergyPlus models were created by modifying the baseline model with each parameter combination. Moreover, the 1000 simulation results were compared with the measured monthly electricity and natural gas usage data to find 29 calibrated solutions. Finally, the 29 calibrated energy models were used to evaluate the energy-saving potential of three energy conservation measures with uncertainty. The retrofit analysis results indicated that the electrical energy saving percentage of chiller replacement ranged from 1.57% to 13.51%, with an average of 8.27%. The energy-saving rate of lighting system replacement ranged from 1.92% to 11.66%, with an average of 6.43%. The energy-saving rate of window replacement ranges from 0.31% to 1.81%, with an average of 0.55%. The results showed that AutoBPS-Param could rapidly create building energy models for existing buildings and can be used for retrofit analysis after model calibration.

Traditionally, building energy model is created in isolation from the architectural building information model and energy analyses have relied on a single analysis tool. The building energy model can be generated more quickly by leveraging existing data from the BIM. The impacts of energy consumption are significant in the building usage phase, which can last several decades. Due to the large share of the final energy consumption in the building sector, accurate analysis of thermal and cooling loads of a building and the efforts to reduce energy losses represent an effective way to reduce energy consumption. Therefore, it is essential to analyze the building energy performance in the design phase, which is when critical decisions are made. This study aims to investigate the impact of the building components and construction materials on building energy efficiency using Building Information Modeling (BIM) technology in a mild climate zone. After reviewing the proposed designs, the main building form was chosen for energy modeling and analysis. Then, building energy consumption analysis was performed based on the basic parameters of the building energy model. Eventually, the most optimal mode was selected by examining different energy consumption forms. This study showed that the building HVAC system always had the largest share of energy consumption. Finally, the results of parametric studies on alternative schemes of energy use intensity optimization showed that 22.59 % savings could be achieved as compared to the base building model in a 30-year time horizon