Vertiv has advanced a production-grade digital twin capability for Vertiv SmartRun, integrating the system into the NVIDIA Omniverse DSX Blueprint for AI factory design and simulation.
The capability is being developed to make high-density AI infrastructure more configurable, repeatable, and simulation-ready before installation. Vertiv SmartRun brings power distribution, liquid cooling, networking, and containment infrastructure into a prefabricated overhead system, while the digital twin captures configurations, dependencies, and engineering intent in a model-based environment.
AI data centre projects now have to align compute roadmaps with physical infrastructure that can take longer to design, procure, and deploy. Power capacity, thermal management, controls, and site coordination are increasingly interdependent, particularly as accelerated computing moves towards higher rack densities and larger facilities.
By shifting planning into a digital model, Vertiv is aiming to reduce the late-stage changes that can occur when power, cooling, controls, and deployment teams work from separate documentation. A single simulation-ready model gives designers a way to assess system choices earlier, preserve engineering intent through commissioning, and support future optimisation once infrastructure is operational.
Scott Armul, chief product and technology officer at Vertiv, said: “AI infrastructure can no longer be planned one compute generation at a time. To deliver more tokens per second per megawatt, customers need power, cooling, controls, and deployment workflows to be designed as one interdependent system. The Vertiv SmartRun digital twin helps encode Vertiv’s infrastructure expertise into configurable, simulation-ready building blocks that support faster, more confident AI factory planning.”
The SmartRun digital twin is the first phase in Vertiv’s wider AI factory digital twin roadmap. Later phases are expected to extend the approach from early configuration and simulation through deployment, commissioning, lifecycle assurance, and optimisation across multiple generations of accelerated computing.
NVIDIA Omniverse DSX Blueprint supports AI factory digital twins using OpenUSD, SimReady assets, and power, thermal, and operational simulations. Vladimir Troy, vice president of AI Infrastructure at NVIDIA, said: “NVIDIA Omniverse DSX Blueprint helps the ecosystem build, simulate, and optimise gigawatt-scale AI factory digital twins using OpenUSD, SimReady assets, and power, thermal, and operational simulations. Bringing Vertiv SmartRun into this workflow can help customers evaluate infrastructure choices earlier and prepare for multiple generations of accelerated computing.”
Vertiv is demonstrating SmartRun at Computex Taipei 2026 as both a physical infrastructure system and a configurable digital twin. The demonstrator has been created using Dassault Systèmes model-based systems engineering capabilities on the 3DEXPERIENCE platform and connected to NVIDIA Omniverse DSX workflows.
Vertiv has released a video on simulation-ready converged physical infrastructure for AI at scale.
