LearningCC: An online learning approach for congestion control

TL;DR

LearningCC introduces an online reinforcement learning-based congestion control method that dynamically selects optimal transmission options, outperforming traditional algorithms especially under random loss conditions, as validated by ns3 simulations.

Contribution

It presents a novel reinforcement learning approach for congestion control that models options as bandit arms and learns optimal choices through trial and error.

Findings

Achieves lower transmission delay than loss-based algorithms.

Significantly improves performance under random loss conditions.

Validated effectiveness through ns3 simulations.

Abstract

Recently, much effort has been devoted by researchers from both academia and industry to develop novel congestion control methods. LearningCC is presented in this letter, in which the congestion control problem is solved by reinforce learning approach. Instead of adjusting the congestion window with fixed policy, there are serval options for an endpoint to choose. To predict the best option is a hard task. Each option is mapped as an arm of a bandit machine. The endpoint can learn to determine the optimal choice through trial and error method. Experiments are performed on ns3 platform to verify the effectiveness of LearningCC by comparing with other benchmark algorithms. Results indicate it can achieve lower transmission delay than loss based algorithms. Especially, we found LearningCC makes significant improvement in link suffering from random loss.