Supercomputing and AI to create digital twin of STEP fusion power plant

5 July 2023

Collaboration between the United Kingdom Atomic Energy Authority (UKAEA), Dell Technologies, Intel and the University of Cambridge is underway to advance the development of the UK’s prototype fusion power plant. Scientists and engineers plan to access supercomputers and AI (artificial intelligence) to inform and accelerate engineering designs of the UKAEA’s STEP (Spherical Tokamak for Energy Production) facility. UKAEA says the engineering designs of STEP, sited in Nottinghamshire, “will be developed in a highly immersive and connected virtual environment, known as the ‘Industrial Metaverse’”.

Working inside the industrial metaverse – a digital representation of an industrial environment that people can interact with – the UKAEA team can adapt their design as new information becomes available and technologies are developed. The supercomputer at the Cambridge Open Zettascale Lab leverages Dell PowerEdge servers based on 4th Gen Xeon processors to run the massive amounts of modelling and simulations needed for fusion research.

oneAPI, which allows developers to use a single codebase to deploy applications across multiple architectures, addresses one of the biggest inhibitors of simulation functionality and performance: code portability. Intel oneAPI tools and optimised AI frameworks deliver performance for deep learning and molecular dynamics. As a oneAPI Centre of Excellence, the Cambridge Open Zettascale Lab is focused on broadening this application set to include engineering, fusion materials and plasma simulation.

Storage speed is another potential roadblock in fusion research, which involves large simulations running across thousands of graphics processing unit nodes and then transferring a huge amount of data for fast post-simulation analysis. A single plasma turbulence simulation can output hundreds of petabytes of data in a very short window. Intel DAOS is an open source, software-defined, scale-out object store that provides high bandwidth, low latency and high I/O operations per second (IOPS) storage containers for high performance computing (HPC) applications. For fusion research, it offers a fast and frictionless pathway for analysis and calculations that need to happen in an incredibly small window of time.

The collaboration will explore how supercomputers – capable of making up to one quintillion calculations per second – and AI technologies with advanced predictive capabilities, can deliver a ‘digital twin’ of STEP. The digital twin “will enable scientists and engineers to create a robust design in the virtual world to ensure ecosystem readiness, value for money and to help STEP achieve its goal of delivering electricity to the grid in the 2040s”, UKAEA explains. Exascale computing – the next generation of computing technology – will provide powerful analytics to test STEP’s initial concepts. The collaboration aims to make the next generation of high-performance computers accessible, practical to use and vendor agnostic.

UK Energy Security & Net Zero Secretary, Grant Shapps, said:

“The world needs fusion energy like never before, has the potential to provide a ‘baseload’ power, underpinning renewables like wind and solar, which is why we’re investing over £700m ($888m) to make the UK a global hub for fusion energy. This new collaboration… ensures the UK solidifies its reputation as a science superpower, turning science fiction to science fact, with the potential for cheaper, cleaner and, crucially, more secure energy.”

According to Dr Rob Akers, Director of Computing Programmes at UKAEA: “Exascale supercomputing, and the advent of the ‘AI era’ are essential and potentially transformative milestones that will help the UK to ensure STEP achieves its mission to connect fusion power to the national grid in the early 2040’s. These powerful technologies will allow us to embed robustness, flexibility, and resilience into the STEP design. I firmly believe the future of sustainable energy will rely upon supercomputing.”

Adam Roe, EMEA HPC Technical Director, Intel, said: “Planning for the commercialisation of fusion power requires organisations like UKAEA to utilise extreme amounts of computational resources and artificial intelligence for simulations. These HPC workloads may be performed using a variety of different architectures, which is why open software solutions that optimise performance needs can lend portability to code that isn’t available in closed, proprietary systems. Overall, advanced hardware and software can make the journey to commercial fusion power lower risk and accelerated – a key benefit on the path to sustainable energy.”

Dr Paul Calleja, Director of Research Computing Services at Cambridge University said the UKAEA’s target of providing fusion energy to the UK grid in the 2040s is an ambitious goal. It needs “equally ambitious advance computing and AI technologies to fuel the virtual engineering effort to create a complete digital reality of the power plant that can be developed and tested in silicon, which greatly accelerates the process”.

The Cambridge Open ZettaScale Lab in partnership with Intel, Dell, UKAEA and a team of HPC experts have been working together for the past two years on a co-design activity called “Project Dawn” to design and prototype a “candidate UK exascale class converged AI & simulation GPU/CPU supercomputer, with the computation power capable of helping UKAEA meet it its vast computational requirements”.

Tariq Hussain, Head of UK Public Sale at Dell Technologies, said: “This project demonstrates the crucial role supercomputing will play in accelerating the energy transition, advancing decarbonisation and ensuring energy security.”

Privacy Policy
We have updated our privacy policy. In the latest update it explains what cookies are and how we use them on our site. To learn more about cookies and their benefits, please view our privacy policy. Please be aware that parts of this site will not function correctly if you disable cookies. By continuing to use this site, you consent to our use of cookies in accordance with our privacy policy unless you have disabled them.