Comparative analysis of machine learning methods for active flow control

Machine learning frameworks such as genetic programming and reinforcement learning (RL) are gaining popularity in flow control. This work presents a comparative analysis of the two, benchmarking some of their most representative algorithms against global optimization techniques such as Bayesian optimization and Lipschitz global optimization. First, we review the general framework of the model-free control problem, bringing together all methods as black-box optimization problems. Then, we test the control algorithms on three test cases. These are (1) the stabilization of a nonlinear dynamical system featuring frequency cross-talk, (2) the wave cancellation from a Burgers' flow and (3) the drag reduction in a cylinder wake flow. We present a comprehensive comparison to illustrate their differences in exploration versus exploitation and their balance between model capacity' in the control law definition versus required complexity'. Indeed, we discovered that previous RL control attempts of controlling the cylinder wake were performing linear control and that the wide observation space was limiting their performances. We believe that such a comparison paves the way towards the hybridization of the various methods, and we offer some perspective on their future development in the literature of flow control problems.

Automated summary

This work presents a comparative analysis of machine learning frameworks such as genetic programming and reinforcement learning in flow control. The algorithms are benchmarked against global optimization techniques and tested on three test cases. The results show differences in exploration versus exploitation and the balance between model capacity and required complexity. The comparison paves the way for hybridization of methods and offers perspectives on future development in flow control problems.