eduzhai > Applied Sciences > Engineering >

Analytic Deep Learning-based Surrogate Model for Operational Planning with Dynamic TTC Constraints

  • Save

... pages left unread,continue reading

Document pages: 8 pages

Abstract: The increased penetration of wind power introduces more operational changesof critical corridors and the traditional time-consuming transient stabilityconstrained total transfer capability (TTC) operational planning is unable tomeet the real-time monitoring need. This paper develops a more computationallyefficient approach to address that challenge via the analytical deeplearning-based surrogate model. The key idea is to resort to the deep learningfor developing a computationally cheap surrogate model to replace the originaltime-consuming differential-algebraic constraints related to TTC. However, thedeep learning-based surrogate model introduces implicit rules that aredifficult to handle in the optimization process. To this end, we derive theJacobian and Hessian matrices of the implicit surrogate models and finallytransfer them into an analytical formulation that can be easily solved by theinterior point method. Surrogate modeling and problem reformulation allow us toachieve significantly improved computational efficiency and the yieldedsolutions can be used for operational planning. Numerical results carried outon the modified IEEE 39-bus system demonstrate the effectiveness of theproposed method in dealing with com-plicated TTC constraints while balancingthe computational efficiency and accuracy.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×