Multi-agent reinforcement learning for wall modeling in LES of flow over periodic hills
This work addresses the challenge of accurate wall modeling in computational fluid dynamics for flows with pressure gradients, which is an incremental advancement in domain-specific applications.
The authors tackled the problem of modeling wall effects in large-eddy simulations of fluid flow over periodic hills by developing a multi-agent reinforcement learning-based wall model that accounts for pressure gradients, resulting in improved predictions of the mean velocity field compared to traditional methods.
We develop a wall model for large-eddy simulation (LES) that takes into account various pressure-gradient effects using multi-agent reinforcement learning (MARL). The model is trained using low-Reynolds-number flow over periodic hills with agents distributed on the wall along the computational grid points. The model utilizes a wall eddy-viscosity formulation as the boundary condition, which is shown to provide better predictions of the mean velocity field, rather than the typical wall-shear stress formulation. Each agent receives states based on local instantaneous flow quantities at an off-wall location, computes a reward based on the estimated wall-shear stress, and provides an action to update the wall eddy viscosity at each time step. The trained wall model is validated in wall-modeled LES (WMLES) of flow over periodic hills at higher Reynolds numbers, and the results show the effectiveness of the model on flow with pressure gradients. The analysis of the trained model indicates that the model is capable of distinguishing between the various pressure gradient regimes present in the flow.