UCL Institute for Environmental Design and Engineering


Blog: Designing sustainable buildings across the world using hybrid-cloud

17 May 2023

UCL Institute for Environment Design and Engineering researchers collaborate with Yellowdog and Feilden Clegg Bradley Studios on mass-simulations of weather effects on buildings

World map with colour coding for the countries

A Blog by Daniel Zepeda-Rivas

The building industry accounts for 39% of global energy-related carbon emissions. Any sustainable future must find a way to reduce this to zero. Daniel Zepeda-Rivas and Ivan from UCL have been focused on doing just that, by creating a library of building designs and 354 million simulations for 500 worldwide locations of the effects on them from a wide range of annual weather conditions. Ultimately, FCBStudios will turn this data into a platform which is available across the world, enabling sustainable buildings design in any climate.

As with many research institutions, capacity of on-premises resource is limited and often fully allocated across a range of world-changing projects. In this instance, that meant the scale and timeline of the project were restricted. In December, YellowDog launched a competition in which we offered $500,000 of cloud compute to selected projects focused on Life Sciences innovation or Carbon Impact reduction. Through a partner organisation called See Through News, Daniel and Ivan successfully applied to the competition.

YellowDog’s platform now enabled the team to access all available compute across the world and rapidly. After initial meetings, both parties were excited about the potential impact of working together and the project team decided to expand their research (by 140 million simulations), beyond what was initially intended to be a resource for UK firms building internationally. Daniel noted:

The possibility to use cloud computing changes the whole timing of the project. Instead of thinking about carrying out a reduced version of the analysis over the next months now we are thinking about a much bigger and more ambitious experimental campaign that can be carried out in weeks.

The team used EnergyPlus, a whole building energy simulation application, modelling detailed building characteristics (708,588 files) and weather conditions (500 international locations) to simulate building design for every set of building and weather condition. 354 million discrete simulations were performed in the cloud on AMD EYPC E4 Flex VMs (virtual machines) with 64 OCPUs (128vCPUs) and 64GB RAM, consuming 45,000 instance hours of compute concurrently across five cloud regions in North America and Europe.

Over the course of 11 calendar days, the full simulation was completed with less than 0.6% failure rate (which were automatically and successfully retried), with the entire simulation creating 37.5TB of data which will now underpin the low-carbon design solutions shared through the open platform. This has drastically accelerated the research (by months) and will potentially have a lasting impact the timeline of international sustainability efforts. If this impact was scaled across research fields, institutions and continents, the potential to accelerate the human race’s understanding of the world is endless.

Often projects of this nature are somewhat sporadic in the use of compute and therefore it’s difficult for academic institutions to purchase enough on-premises machines to satisfy all researchers at once. Therefore, by using a hybrid-cloud setup and accessing available (and often idle) compute across the world, this can be scaled and accelerated. Organisations often require help getting to hybrid-cloud or multi-cloud capability, opting to avoid lengthy on-boarding and knowledge intensive processes.

As demonstrated by the nature of this project’s completion, YellowDog’s expert team can rapidly onboard teams and simulations of this type on the platform, enabling world-leading scale and execution. In the case of Daniel and Ivan, enabling the global propagation of the knowledge required to build sustainable buildings, anywhere.