How Machine Learning can help Optimization modeling

  • 30 May 2019
  • 0 replies
  • 509 views

Userlevel 4
Badge +1



Dear AIMMS communians­čśë,

We started some years ago at AIMMS an investigation on how machine learning and optimization can work together, or how machine learning algorithms could help optimization modeling.

During the AIMMS Summit, in addition to the very interesting presentation from Ger Koole, we presented a 45 min workshop demoing an interesting use case on this matter - Optimizing a power production plan with renewable resources. This example showcases a combination between machine learning and robust optimization. I'm sharing now our slides, as well as the model itself, written in AIMMS.

This example was greatly inspired and helped by Gianmaria Leo, an IBM researcher we met at the EWG POR Conference in Bologna in March 2019. Thank you Gianmaria!
You may find his open source repository here.

The idea of sharing it now is to start a discussion, share our upcoming progress, gather your thoughts, inspirations and potential contributions. We believe this subject would greatly benefit from a community investigation.

As you can see in the attached project, the Stochastic approach was not modeled yet Ôś║´ŞĆ Don't hesitate to improve it and re-post it!

0 replies

Be the first to reply!

Reply


Didn't find what you were looking for? Try searching on our documentation pages:

AIMMS Developer & PRO | AIMMS How-To | AIMMS SC Navigator