Monte Carlo with BuildSim Cloud
The parametric module on BuildSim Cloud is now equipped with Monte Carlo method!
Monte Carlo method is a broad class of computational algorithms that discover numerical results through repeated samplings from inputs. It is often used in the modeling field for uncertainty analysis, design optimization and ML training.
The algorithms behind Monte Carlo method is the Latin Hypercube sampling. This sampling can effectively reduce the number of samples required for target value estimation. Compare to the brute force algorithm, which could require thousands of simulations; this algorithm need 100-200 simulations, which is significantly time-saving.
It is simple to activate the MC algorithm through BuildSim API library - The procedure is the same as the regular parametric study with a few modifications.
1. Energy efficient measures:
When defining EEMs, instead of giving a list of variables for testing, we need to define the minimum and maximum values:
2. Submit parametric request:
Switch the algorithm parameter to 'montecarlo' and also specify the size of the simulation.
That's it! To learn more story about BuildSim Cloud parametric study, check out the our parametric wiki page.
To see the full example code of monte carlo, check out this link.