Title: Machine Learning for Power Systems: Physics-Informed Neural Networks and Verification
Date: April 22, 2020
Bio: Spyros Chatzivasileiadis (S’04, M’14, SM’18) is an Associate Professor at the Technical
University of Denmark (DTU). Before that he was a postdoctoral researcher at the Massachusetts
Institute of Technology (MIT), USA and at Lawrence Berkeley National Laboratory, USA. Spyros holds
a PhD from ETH Zurich, Switzerland (2013) and a Diploma in Electrical and Computer Engineering
from the National Technical University of Athens (NTUA), Greece (2007). In March 2016, he joined
the Center for Electric Power and Energy at DTU. He is currently working on power system optimization
and control of AC and HVDC grids, and machine learning applications for power systems.
Abstract: In this tutorial, we introduce methods that remove the barrier for applying neural networks
in real-life power systems, and unlock a series of new applications. First, we introduce a framework for
verifying neural network behavior in power systems. Up to this moment, neural networks have been
applied in power systems as a black-box; this has presented a major barrier for their adoption in practice.
Using a rigorous framework based on mixed integer linear programming, our methods have the potential
to build the missing trust of power system operators in neural networks. Second, we present a framework
for physics-informed neural networks in power system applications. Exploiting the underlying physical
laws governing power systems, and inspired by recent developments in the field of machine learning,
we propose a neural network training procedure that can make use of the wide range of mathematical
models describing power system behavior. Methods such as the ones we will discuss in this talk unlock
the potential of neural networks to perform power system tasks at extremely fast computing times while
maintaining verified accuracy.