Real world operations of grid batteries, DERs, and virtual power plants often differ from idealized models. Optimization and machine learning techniques in the energy domain require much nuance that is often not recognizable until projects are live. In this talk, I’ll run through some examples of energy asset operations driven by AI platforms where unexpected conditions require different approaches to achieve high performance. This will lead into a discussion about how electric vehicles may leverage these lessons to become a valuable grid asset if controlled in aggregate as "mobile power plants".

The seminar is open to the public. Stanford students enrolled in CEE 272T/EE 292T: SmartGrids and Advanced Power Systems Seminar must attend in person. All others, please register to attend.