Cyber security for energy management & AI in Power Systems
10:00 – 10:40
Talk by Professor Tobias Oechtering, KTH, Sweden
Title: Energy management for smart meter privacy and more
----- SHORT BREAK ----------------------------------------------------------------------
10:45 – 11:25
Talk by Professor Anna Scaglione, Cornell University, USA
Title: AI methods for grid data and control
Date and Time
Location
Hosts
Registration
- Date: 02 Apr 2024
- Time: 10:00 AM to 11:30 AM
- All times are (UTC+02:00) Copenhagen
-
Add Event to Calendar
- Contact Event Host
- Co-sponsored by Technical University of Denmark
Speakers
Tobias Oechtering of KTH
Energy management for smart meter privacy and more
In this talk, we will discuss the design problem of consumer privacy-preserving energy management strategy for smart meter privacy. The goal of the privacy-by-design approach is to change the energy consumption profile to lower adversarial inference attacks. We will discuss different design approaches and present some experimental results. In the second part of the talk, we will give a brief introduction to a novel information-theoretic privacy measure called pointwise maximal leakage that is operationally meaningful, robust, and flexible. The definition is again based on an adversarial inference attack formulation. As a result of the robust formulation, provable privacy guarantees are given by simple upper bounds on the information density which makes the formulation very attractive.
Biography:
Tobias Oechtering received his Dipl.-Ing. degree in Electrical Engineering and Information Technology in 2002 from RWTH Aachen University, Germany, and his Dr.-Ing. degree in Electrical Engineering in 2007 from the Technische Universität Berlin, Germany under the supervision of Prof. Holger Boche. In 2012 he became Docent in Communication Theory at KTH Royal Institute of Technology. In November 2008 he joined the Communication Theory Lab at KTH as a Post-Doctoral Researcher, was an Assistant Professor between July 2010 and April 2013, an Associate Professor between May 2013 and October 2018 and has been a Professor since Nov 2018. He served as Associate Editor of the IEEE Communication Letters between Feb 2012 and March 2015. Presently, he is serving as a senior editor for IEEE Transactions on Information Forensics and Security since June 2020, previously as editor since 2016.
Address:Sweden
Anna Scaglione of Cornell University
AI methods for grid data and control
There is a flurry of research activities recently focusing on applications of Artificial Intelligence in electric power systems analysis and operation. It is often motivated by emerging trends that are tied to decarbonizing the grid through the adoption of distributed renewable energy sources and demand response programs that call for methods account for the stochasticity of the net-demand. The vast majority of the research takes AI tools as a black box that internalizes every aspect of the observations, including the physics of the system (namely Ohm’s law) and learns to control the system by being rewarded in choosing good actions. In this talk we discuss how to go a step further. First, we introduce Complex Graph Neural Network and show that they are most effective in both inference and reinforcement learning tasks, thanks to their physics inspired feature extraction capabilities. Then we move to introduce the problem of “safe” reinforcement learning, which allows to enforce the physical and safety constraints in the optimal policy.
Biography:
Anna Scaglione is a professor of electrical and computer engineering at Cornell Tech, the New York City campus of Cornell University. She has previously held faculty positions at Arizona State University, the University of California at Davis, Cornell University, and the University of New Mexico. She received her M.Sc in 1995 and Ph.D in 1999. She is a Fellow of IEEE since 2011 and has received many awards such as the 2013 IEEE Donald G. Fink Prize Paper Award, the 2000 IEEE Signal Processing Transactions Best Paper Award, and the NSF CAREER grant (2002). She has also received several best student papers awards at conferences and was Distinguished Lecturer of the Signal Processing Society in 2019 and 2020. Dr. Scaglione's research focus is on theoretical and applied problems n statistical signal processing, distributed optimization and cyber-physical systems, with particular interest on sustainable energy delivery systems. Her talk will include some of her latest research results on novel AI architectures that are tailored to the unique features of electric power systems.
Address:United States
Agenda
10:00 – 10:40
Talk by Professor Tobias Oechtering, KTH, Sweden
Title: Energy management for smart meter privacy and more
----- SHORT BREAK ----------------------------------------------------------------------
10:45 – 11:25
Talk by Professor Anna Scaglione, Cornell University, USA
Title: AI methods for grid data and control