Serverless computing for mathematical optimization

We consider a real case study. In creating power market scenarios, we need to find the energy dispatch of batteries: an optimization problem with hundreds of thousands of variables.

Fortunately, the problem can be split into subproblems which can be solved in parallel.

We show how a serverless approach based on cloud functions can cut the elapsed time by 96% wrt a virtual machine while keeping the operating costs as low as 3€ per run.

After attending this talk, you will be aware of the capabilities of serverless for high-performance computing and have a better feeling about how to design a cloud architecture.