Combining Heuristic and Reinforcement Learning to Achieve the Low-latency and High-throughput Receiver-side Congestion Control

TL;DR

This paper introduces Nuwa, a receiver-driven congestion control framework that uses one-way delay detection and reinforcement learning to improve throughput and reduce delay in dynamic network conditions.

Contribution

It proposes a novel receiver-side congestion control method combining delay monitoring and reinforcement learning for better adaptability and performance.

Findings

Nuwa improves TCP throughput by 4% to 15.4%.

Nuwa reduces average queueing delay by 6.9% to 29.4%.

Reinforcement learning enhances Nuwa's adaptability.

Abstract

Traditional congestion control algorithms struggle to maintain the consistent and satisfactory data transmission performance over time-varying networking condition. Simultaneously, as video traffic becomes dominant, the loose coupling between the DASH framework and TCP congestion control results in the un-matched bandwidth usage, thereby limiting video streaming performance. To address these issues, this paper proposes a receiver-driven congestion control framework named Nuwa. Nuwa deploys the congestion avoidance phase at the receiver-side, utilizing one-way queueing delay detection to monitor network congestion and setting specific target delays for different applications. Experimental results demonstrate that, in most cases, with appropriate parameter configuration, Nuwa can improve the throughput of TCP flows 4% to 15.4% and reduce average queueing delay by 6.9% to 29.4%. Furthermore, we also introduce the use of reinforcement learning to dynamically adjust Nuwa's key parameter , enhancing Nuwa's adaptability to the unpredictable environment.