Drag-reduction strategies in wall-bounded turbulent flows using deep reinforcement learning

TL;DR

This paper compares traditional and deep reinforcement learning-based drag-reduction strategies in turbulent flows, demonstrating that DRL can discover more effective control policies using flow information at specific wall-normal locations.

Contribution

It introduces a reinforcement learning interface for fluid simulations and shows that DRL can outperform existing drag-reduction methods in turbulent channel flow.

Findings

DRL-based policies outperform traditional opposition control.

Deep deterministic policy gradient effectively discovers control strategies.

Flow information at specific wall-normal locations enhances control effectiveness.

Abstract

In this work we compare different drag-reduction strategies that compute their actuation based on the fluctuations at a given wall-normal location in turbulent open channel flow. In order to perform this study, we implement and describe in detail the reinforcement-learning interface to a computationally-efficient, parallelized, high-fidelity solver for fluid-flow simulations. We consider opposition control (Choi, Moin, and Kim, Journal of Fluid Mechanics 262, 1994) and the policies learnt using deep reinforcement learning (DRL) based on the state of the flow at two inner-scaled locations ($y^+ = 10$ and $y^+ = 15$). By using deep deterministic policy gradient (DDPG) algorithm, we are able to discover control strategies that outperform existing control methods. This represents a first step in the exploration of the capability of DRL algorithm to discover effective drag-reduction policies using information from different locations in the flow.