This digital twin platform connects to the industry-standard Building Performance Simulation engine, EnergyPlus™, to conduct building energy scenario analysis. It addresses a critical gap in the architecture, engineering, and construction (AEC) industry to perform high-fidelity, real-time energy analysis on complex building systems. Buildings account for a significant amount of global energy consumption and greenhouse gas emissions. At a national level, they represent a significant lever for national energy conservation, with the combined residential and commercial sectors accounting for approximately 37% of total U.S. energy consumption when accounting for electricity-generation losses. Despite the availability of modern Building Information Modeling (BIM), current systems often struggle to bridge the gap between static architectural data and dynamic, physics-based performance analysis. Existing building management approaches and simulation tools are often limited by fragmented data silos and a lack of real-time integration.
Traditional methods frequently rely on static models that do not account for real-time environmental factors or human-related drivers, such as occupant behavior and operational maintenance; these can influence energy outcomes as significantly as physical building properties. Furthermore, standard simulation engines like EnergyPlus™ typically require bespoke, labor-intensive integrations for each new building model, preventing the scalable, "on-the-fly" analysis necessary for modern facility management. The global market for digital twin technology is rapidly expanding as a crucial concept for improving productivity and reducing downtime across the built environment. By 2023, the significance of building energy profiles has underscored a growing need for robust improvement strategies that can forecast energy demands and simulate complex heating, ventilation, and air conditioning (HVAC) loads with precision. However, the industry still faces a lack of seamless, bi-directional interfaces for visualizing both building states and predicting future performance through automated "what-if" scenario testing.
University of Florida researchers have developed a computing system featuring a bi-directional connector module that interfaces with high-fidelity digital twin platforms, such as NVIDIA™ Omniverse, with the industry-standard EnergyPlus™ simulation engine. This framework leverages a layered architecture, comprising hardware, middleware, and software, to create a dynamic virtual replica of physical assets that is continuously updated with real-time IoT sensor data. By decoupling the digital twin from the simulation engine through a generic connector, this approach enables scalable, real-time decision support and predictive maintenance, offering a transformative solution for energy efficiency and providing building operators with actionable insights to reduce global greenhouse gas emissions. This tool offers valuable data for advancing energy-efficient architectural designs.
Seamless, interactive building energy decision-making platform for conducting building energy scenario analysis and performance optimization and prediction through high-fidelity digital twin visualization and physics-based simulation
Performing building energy analysis involves using a high-fidelity digital twin platform, a bi-directional connector module, and a physics-based simulation engine. Static geometric data from a Building Information Model (BIM) enters the platform, integrates with real-time operational data from IoT sensors, and reaches the simulation engine. Next, a bi-directional loop is established between the virtual replica and the simulation engine, and "what-if" scenarios are executed. Performance results are quantified by analyzing the output data returned from the engine to the digital twin interface. The ratio of energy consumption to specific operational variables is then calculated to provide near real-time visual feedback. These measurements provide valuable insights, enabling building operators to make informed decisions about a building’s energy efficiency.