One of the big challenges in computer-based design is the
amount of processing power required to simulate how designs will
perform in the real world.
Electronic simulations of a wind tunnel allow designers to
analyse the performance of a component or product without having to
build a prototype. Computers allow designers to perform this task,
but it has traditionally involved using expensive supercomputers or
high-performance computing clusters, which need teams of experts to
maintain. For instance, the Renault Formula 1 team has invested
£350m in a
computational aerodynamics research centre to run race
simulations on car designs.
Putting the computational processing power in the cloud reduces
this overhead. Southampton start-up
dezineforce has developed
a hosted engineering design optimisation service. This software as
a service (SaaS) offering gives users access to an integrated suite
of tools for the analysis of design behaviour and for systematic
search.
Collaborative working
As well as design optimisation software, the suite includes
high-performance cluster computing and simulation applications for
structural, fluid dynamics and mechanism analysis using Microsoft
Windows HPC Server 2008. Because the tools are delivered over the
internet, they can be accessed from anywhere in the world, by
whoever the subscribing company chooses, facilitating collaboration
between teams at different locations.
The team behind dezineforce include professors Simon Cox,
director of the
Microsoft Institute for High Performance Computing at the
University of Southampton, and Andy Keane, director of the
Rolls-Royce University Technology Centre for Computational
Engineering at the University of Southampton. Customers include
global design and engineering firm Arup, along with small design
consultancy businesses and specialist manufacturers.
The company has shown what SaaS can do for engineering at
several events this year. It recently demonstrated a wind farm
optimisation simulation with a company called Intelligent Fluid
Solutions, which used the dezineforce service to simulate the
optimal position for wind turbines on a wind farm. The service
allowed Intelligent Fluid Solutions to run the simulation as a
cloud service, without the need to invest in a high-performance
computing cluster.
Microsoft platform
The dezineforce service uses a Microsoft platform which includes
Internet Information Services (IIS) 7.0 and ASP.net, together with
Ajax programming. A 3D visualisation tool is implemented as a
Windows Presentation Foundation (WPF) browser application, which
provides hardware-accelerated, interactive 3D visualisation within
a browser, without the need to install software.
Cox says dezineforce is more suited to the way engineering
projects are run, compared with other ways of providing
high-performance computing. "Engineering is very project-based.
There is an intense level of activity then a quiet period," he
says.
An in-house high-performance computing cluster will be mostly
idle during these quiet periods. As such, Cox says high-performance
computing in the cloud is a better option, because users only pay
when they need the computational resource.
The company says its IT infrastructure has been built to run,
schedule and secure multiple engineering simulations in the
cloud.
Cloud computing certainly looks like the next big wave that is
hitting the IT industry. If dezineforce is successful in convincing
businesses both large and small to run computational simulations in
the cloud, it will prove that cloud computing can be used for some
of the world's most complex computational tasks.