AI RESEARCH

Optimal Control of Multiclass Fluid Queueing Networks: A Machine Learning Approach

arXiv CS.LG

ArXi:2307.12405v2 Announce Type: replace We propose a machine learning approach to the optimal control of multiclass fluid queueing networks (MFQNETs) that provides explicit and insightful control policies. We prove that a piecewise constant optimal policy exists for MFQNET control problems, with segments separated by hyperplanes passing through the origin. We use Optimal Classification Trees with hyperplane splits (OCT-H) to set and apply OCT-H to learn explicit control policies.