[Defense] AI Enhanced Design for Resilient Cyber-Physical Systems
Tuesday, November 15, 2022
1:00 pm - 2:00 pm
In
Partial
Fulfillment
of
the
Requirements
for
the
Degree
of
Doctor
of
Philosophy
S
M
Salah
Uddin
Kadir
will
defend
his
proposal
AI
Enhanced
Design
for
Resilient
Cyber-Physical
Systems
Abstract
Cyber-physical system operations like power grid operations are subject to extreme events that require human operators’ decision-making under stressful conditions with high cognitive load. Decision-making under adverse dynamic events should be supplemented by intelligent proactive control, especially if forecast. Power system operation during wildfires requires resiliency-driven proactive management for load shedding, line switching, and resource allocation considering the wildfire dynamics and failure propagation. However, the possible number of line and load switching in an extensive system during an event makes traditional prediction-driven and stochastic approaches computationally intractable, leading operators to often use greedy algorithms. We model and solve the proactive control problem as a Markov decision process and introduce an integrated testbed for spatio-temporal wildfire propagation and proactive power-system operation. Our approach allows the controller to provide setpoints for all generation fleets. We evaluate our approach utilizing the IEEE 24-node system mapped onto a hypothetical terrain. Our experimental results show that it can help the operator to reduce load loss during an extreme event. It also reduces power flow through lines that are to be de-energized and adjusts the load demand by increasing power flow through other lines. Although our current approach effectively reduces load loss during extreme events, we aim to improve our current approach in the future.
Tuesday,
November
15,
2022
1:00PM
-
2:00PM
CT
Online
via
Â
Dr. Stephen Huang, dissertation advisor (for Dr. Aron Laszka)
Faculty, students and the general public are invited.
