[CCoE Notice] ECE Seminar- Monday, April 10

[Hutchinson, Inez A]

Dear Engineering Community,

Seminar title:     Scalable Designs for Reinforcement Learning based Optimal Control of Large-Scale Networks: Applications to Electric Power Systems

Speaker:              Prof. Aranya Chakrabortty, North Carolina State University (NSF Program Director in the ECCS division)

Date & Time:      10:00 AM, Monday, April 10, 2023

Zoom Meeting room:

https://urldefense.com/v3/__https://zoom.us/j/9762699678?pwd=RUp5ZmN3cHUyQ1FvUExVQjVsc1hVUT09__;!!LkSTlj0I!HoONsRbKA1lAGBSmwOPzE2nhU09RnoA_DGSCWTxu_j7WL06mPVmg58CSlimZFavvJsvQLMFA2M1VgopwHmDAlaBSuC4$ <https://urldefense.com/v3/__https:/zoom.us/j/9762699678?pwd=RUp5ZmN3cHUyQ1FvUExVQjVsc1hVUT09__;!!LkSTlj0I!EL8uyUw3s8XdqvdzNnYVH6bY-AI9dNcAq73XTbcTNBgCiAnOT0ZKmmmkGv8qFvfAVOcmSTo8pG7zsGxDbpWALGeulzE$>

Meeting ID: 976 269 9678

Passcode: K91Bwy



Seminar Abstract: Reinforcement Learning (RL) is an effective way of designing model-free linear quadratic regulator (LQR) controllers for linear time-invariant (LTI) networks with unknown state-space models. However, when the network size is exceptionally large as in many practical systems such as electric power grids or transportation networks, conventional RL can result in unacceptably long learning times, making it impossible to control the network in real-time. In this talk, I will present some new designs that resolve this problem by combining different variants of dimensionality reduction with RL theory. I will specifically discuss the scenario when the network model exhibits a time-scale separation in its dynamics. Singular perturbation theory will be used for the dimensionality reduction and approximation of the RL controller, followed by stability proofs and optimality analysis. Validation examples will be shown for RL-based wide-area oscillation damping control of the IEEE prototype power system models.


Speaker Bio: Dr. Aranya Chakrabortty received his PhD degree from Rensselaer Polytechnic Institute, Troy, New York, in 2008 in electrical engineering. He is currently a professor of Electrical and Computer Engineering at North Carolina State University. His research interests include all branches of control theory with applications to electric power systems. Since 2020, Aranya has also been serving as a program director at the National Science Foundation, where he manages the power system program in the ECCS division under the engineering directorate.


Thank you!
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://Bug.EGR.UH.EDU/pipermail/engi-dist/attachments/20230405/af062552/attachment-0001.html 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: ECE Seminar Flyer_ Dr_Aranya_Chakrabortty.pdf
Type: application/pdf
Size: 651523 bytes
Desc: ECE Seminar Flyer_ Dr_Aranya_Chakrabortty.pdf
Url : http://Bug.EGR.UH.EDU/pipermail/engi-dist/attachments/20230405/af062552/attachment-0001.pdf