Notes

Title:
Quantifying and exploiting flexibility in EV charging: data-driven modeling and reinforcement learning

Abstract:
The modern power grid is facing various challenges that gave rise to the adoption of smart grids. One such challenge is the increasing penetration of distributed renewable energy sources (DRES), another the anticipated electrification of transportation (i.e., electric vehicles). Part of the smart grid solution lies in demand response (DR) approaches to try and match the available production by adapting the flexibility in power consumption, i.e., shift consumption in time.
This presentation will highlight research that pertains to "knowing" power consumption, as a necessary condition for "controlling" it. For the former part, we will present results from data analytics on clustering and modeling user behavior in electric vehicle (EV) charging, in terms of total power consumption and the flexible portion thereof. For the latter, we will introduce a reinforcement learning (RL) approach to jointly control a whole set of EVs at once.

Speaker: prof. dr. ir. Chris Develder, Ghent University - imec

Bio: Chris Develder is associate professor with the research group IDLab in the Department of Information Technology (INTEC) at Ghent University - imec, Ghent, Belgium. He received the MSc degree in computer science engineering and a PhD in electrical engineering from Ghent University (Ghent, Belgium), in July 1999 and December 2003 respectively (as a fellow of FWO). He has stayed as a research visitor at UC Davis, CA, USA (Jul.-Oct. 2007) and at Columbia University, NY, USA (Jan. 2013 - Jun. 2015). Chris currently leads two research teams within IDLab, one on converting text to knowledge (i.e., natural language processing, mostly information extraction using machine learning), the other on data analytics and machine learning for smart grids. Together with his team, Chris has published more than 200 papers in international journals and conferences.