Back in the days, when I was racing in sailing, there was a problem. I was trying to run too complex simulations in my head... there are so many variables that affect the outcome and most of those cannot be predicted. So I learned to trust my gut.
In any operations, we have been facing the similar problem, we want to optimise, but to which level could it be taken. First of all, you need to collect and combine the data, then start building algorithms to understand it and run those somewhere. The more complex algorithms are, the more time it takes to run those and some may not add too much value.
I am really thrilled about the possibilities that are not even too far in the future. We are getting cost-efficient sensors that can use solar power, so we can tag anything, we are getting smart connectivity solutions to collect the data, digital twin solutions are starting to help us to compare the simulations with the real life data and the next-gen computing makes it possible to run those complex simulations and start utilising machine learning to gradually improving the outcome.
Of course this is complex, but we have amazing in-house technologies and even more amazing partners to put this together. I am really hoping that we start piloting these solutions in the near future and if you are interested to hear more, please feel free to ping me.
In Fujitsu's in-house usage, Digital Annealer optimized movements for picking up parts stored in a warehouse at a production site, successfully reducing transfer distances by 20%. By optimizing the locations of parts inside the warehouse, Digital Annealer can further reduce movement distances by up to 45%.