ENBIS Webinar by Chris Develder: "Data analytics and machine learning applied to the smart grid: Knowing and controlling electric vehicle charging"10 December 2020; 12:00 – 13:00
Data analytics and machine learning applied to the smart grid: Knowing and controlling electric vehicle charging
Chris Develder, Ghent University - imec, Belgium
The current power grid is facing challenges, including among others (i) the increasing penetration of distributed renewable energy sources (DRES), as well as (ii) the electrification of transportation (i.e., electric vehicles). Demand response (DR) approaches to try and match the available production by adapting the flexibility in power consumption, e.g., shift consumption in time, form one part of the answer to address these challenges.
This presentation will highlight our research on electric vehicle (EV) charging that pertains to "knowing" the resulting power consumption, as a necessary condition for "controlling" it. For the "knowing" 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. We will also point to our recent models for generation of synthetic EV charging session data, which reflects behavior from a large-scale real-world dataset.
For the "controlling part", we will introduce our reinforcement learning (RL) approach for DR, to jointly control a whole set of EV charging stations at once.
Chris Develder is associate professor with IDLab in the Department of Information Technology (INTEC) at Ghent University - imec, Ghent, Belgium. He received an MSc in computer science engineering in 1999, and a PhD in electrical engineering in 2003, both from Ghent University. He stayed as a research visitor at UC Davis, CA, USA (Jul.-Oct. 2007) and at Columbia University, NY, USA (2013-2015).
Chris leads two research teams within IDLab, one on converting text to knowledge (NLP, mostly information extraction using machine learning), the other on data analytics and machine learning for smart grids. With his teams, he co-authored 200+ papers.