Machine Learning for Power Systems: Is it time to trust it?

Abstract: 
In this talk, we introduce methods that remove the barrier for applying neural networks in real-life power systems, and unlock a series of new applications. More specifically, we introduce a framework that addresses five key challenges (dataset generation, data pre-processing, neural network training, verification, and embedding in other tools) associated with building trustworthy ML models which learn from physics-based simulation data. We introduce methods for (i) physics-informed neural networks in power systems,  (ii) verifying neural network behavior in power systems and (iii) obtain provable worst-case guarantees of their performance. 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 can obtain provable worst-case guarantees of the neural network performance. Such methods have the potential to build the missing trust of power system operators on neural networks, and unlock a series of new applications in power systems and other safety-critical systems.
 
Short Bio: 
Spyros Chatzivasileiadis is the Head of Section for Power Systems and an Associate Professor at the Technical University of Denmark (DTU). Before that he was a postdoctoral researcher at MIT and Lawrence Berkeley National Lab, 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). He is currently working on trustworthy machine learning for power systems, quantum computing, and on power system optimization, dynamics, and control of AC and HVDC grids. Spyros has received the Best Teacher of the Semester Award at DTU Electrical Engineering, and is the recipient of an ERC Starting Grant in 2020.