Cloud-based simulation of pipeline components in the oil&gas industry
Dynaflow Research Group (DRG), the end user of this experiment, is an SME that provides engineering consulting services to global leading oil & gas companies. For its computational fluid dynamics (CFD) needs, in particular simulation of pipelines, DRG relies on the open-source based CFD package HELYX developed and distributed by ENGYS, the ISV partner of this experiment. With the help of NAG, the HPC partner, ENGYS is to develop a technical solution around HELYX (based on popular open-source CFD package OpenFOAM) to enable cloud-based simulations to facilitate access to HPC resources for companies such as DRG. ENGYS will refactor HELYX to use a client-server model so that simulations on HPC platforms can be remotely steered by the end user via a friendly graphics user interface. NAG will support ENGYS by deploying OpenFOAM on an HPC platform (EPCC's Indy) and establishing state-of-the-art technical solutions for tasks such as remote visualisation. Dynaflow will evaluate this service with two representative test cases. This experiment will give Dynaflow a competitive edge by the capability to run large CFD simulations at scale from a simple desktop environment with improved efficiency and accuracy. The enhanced HELYX software offering pay-per-use access to HPC resources with remote visualisation is to help ENGYS gain new customers and increase its share in the CFD market, especially within the SME sector. With the acquired experience, NAG is to further enhance its expertise in HPC services.
For many SMEs in the engineering and manufacturing sectors, in-house computing hardware is usually insufficient for solving large problems. This is the case for the CFD simulations required by DRG for oil & gas applications. Furthermore, the initial investment required to acquire in-house HPC resources is often prohibitive, in particular for businesses with occasional CFD usage. On-demand cloud-based HPC solutions, combined with software based on open-source technologies, can offer a more cost-effective alternative. The main challenge faced by DRG and its partner ENGYS was to create a new methodology to perform oil & gas CFD simulations using on-demand cloud-based HPC solutions in a similar fashion as computations perform using in-house hardware resources.
ENGYS developed and tested a novel client-server framework for their CFD software HELYX® with the help of NAG and DRG. The new client-server framework allows end-users to perform CFD simulations on remote HPC hardware directly from a desktop Graphical User Interface. The new technology facilitates access to and effective use of remote HPC resources from a local desktop, such as those employed by DRG. The introduction of the client-server module in HELYX® also opens the possibility of providing this product on a short-term licence as an on-demand service, which could be promoted and delivered via the Fortissimo Marketplace and other similar platforms.
A simple calculation based on the work in this experiment showed that the costs to DRG of buying and maintaining a computer cluster in-house for performing these CFD simulations can be as much as 5 times higher than the costs associated with the equivalent cloud-based HPC solution. In addition, there is a clear benefit of faster turn-round times for the simulations, as well as the opportunity to perform much larger computations using a cloud-based HPC platform. The simulations can be as much as 10 times faster with potential savings of €2,000 per simulation per day, based on standard industry consultancy rates for relevant consultancy projects.
The new client-server approach in HELYX® is also expected to increase sale opportunities for ENGYS by as much as 20%, thanks to the introduction of short-terms licenses for on-demand usage of the software in the cloud. Furthermore, the possibility of providing these resources via the Fortissimo Marketplace should lead to increased revenue by exposure to a wider market.
EPCC will see an increase in its commercial activities through extended use of its commercial supercomputer platforms. NAG will create case studies based on this experiment to showcase its capability in software engineering and high-performance computing. Such marketing materials will be distributed to potential customers to attract new HPC consulting business. Current estimates are that this would result in an additional revenue for NAG in excess of €150K over the next three years.