Towards Fair and Efficient Learning-based Congestion Control

arXiv:2403.01798v1 Announce Type: cross
Abstract: Recent years have witnessed a plethora of learning-based solutions for congestion control (CC) that demonstrate better performance over traditional TCP schemes. However, they fail to provide consistently good convergence properties, including {\em fairness}, {\em fast convergence} and {\em stability}, due to the mismatch between their objective functions and these properties. Despite being intuitive, integrating these properties into existing learning-based CC is challenging, because: 1) their training environments are designed for the performance optimization of single …

abstract arxiv congestion control convergence cs.lg cs.ni fair fairness functions good performance solutions stability type