Cloud-based simulation environment for CO2 emission prediction for automotive engines

The result of this Fortissimo experiment is a demonstration of how SMEs in the automotive industry can perform large-scale simulations without the need for a large primary investment in computational hardware and permanent software licences. This will enable improvements in design that can optimize of a vehicle’s architecture in order to reduce CO2 emissions. In contrast to the traditional approach, this experiment utilised cloud-based HPC computing which allows many simulation tasks to run simultaneously, following to a customisable schedule and results to be obtained in a shorter time. This simulation service together with a tool for the analysis of results can be offered to SME end-users within a user-friendly, web-based front-end environment, enabling them to access and perform large-scale parameter studies as needed, when needed, whilst preserving control over progress and results. The most clear cost benefit to SMEs of using Cloud-based HPC resources is the possibility to lease a powerful computer system for single projects instead of acquiring and maintaining computational resources which would be underutilized most of the time and which would probably not be sufficient when really needed. Clearly, the pay-per-use approach both the computing cycles and to software licences is of significant benefit to such organisations. This leads to a better management of computational and development resources, opening a whole new set of applications such as extensive parameter variations.