LFQ: Online Learning of Per-flow Queuing Policies using Deep Reinforcement Learning

TL;DR

This paper introduces LFQ, an online deep reinforcement learning-based fair queuing mechanism that dynamically optimizes per-flow buffer sizes to improve network fairness and efficiency.

Contribution

It presents a novel AQM mechanism using deep reinforcement learning to adaptively learn optimal per-flow queue sizes in real-time.

Findings

LFQ achieves smaller queues than traditional methods.

LFQ maintains or improves throughput compared to existing schedulers.

LFQ adapts to different congestion control algorithms effectively.

Abstract

The increasing number of different, incompatible congestion control algorithms has led to an increased deployment of fair queuing. Fair queuing isolates each network flow and can thus guarantee fairness for each flow even if the flows' congestion controls are not inherently fair. So far, each queue in the fair queuing system either has a fixed, static maximum size or is managed by an Active Queue Management (AQM) algorithm like CoDel. In this paper we design an AQM mechanism (Learning Fair Qdisc (LFQ)) that dynamically learns the optimal buffer size for each flow according to a specified reward function online. We show that our Deep Learning based algorithm can dynamically assign the optimal queue size to each flow depending on its congestion control, delay and bandwidth. Comparing to competing fair AQM schedulers, it provides significantly smaller queues while achieving the same or higher throughput.