BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Discovering drag reduction strategies in wall-bounded turbulent fl
 ows using deep reinforcement learning - Luca Guastoni (KTH - Royal Institu
 te of Technology)
DTSTART:20230424T133000Z
DTEND:20230424T143000Z
UID:TALK198406@talks.cam.ac.uk
DESCRIPTION:Deep reinforcement learning (DRL) is a mathematical framework 
 that has been used to design and learn control policies in different domai
 ns\, and several applications in physics research have been proposed\, as 
 well. Here we introduce a reinforcement learning (RL) environment to desig
 n control strategies for drag reduction in turbulent fluid flows enclosed 
 in a channel. The control is applied in the form of blowing and suction at
  the wall\, while the observable state is the velocity in the streamwise a
 nd wall-normal directions\, at a given distance from the wall.Given the co
 mplex nonlinear nature of turbulent flows\, the control strategies propose
 d so far in the literature are physically grounded\, but too simple. DRL\,
  by contrast\, enables leveraging the high-dimensional data that can be sa
 mpled from flow simulations to design advanced control strategies.In an ef
 fort to establish a benchmark for testing data-driven control strategies\,
  we compare opposition control\, the state-of-the-art turbulence-control s
 trategy from the literature\, and a commonly-used DRL algorithm\, deep det
 erministic policy gradient. Our results show that DRL leads to 43% and 30%
  drag reduction in a minimal and a larger channel (at a friction Reynolds 
 number of 180)\, respectively\, outperforming the classical opposition con
 trol by around 20 and 10 percentage points\, respectively.\nCo-authors: Je
 an Rabault (Norwegian Meteorological Institute)\, Philipp Schlatter (KTH -
  Royal Institute of Technology)\, Hossein Azizpour (KTH - Royal Institute 
 of Technology) and Ricardo Vinuesa (KTH - Royal Institute of Technology)
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR