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

by   Maximilian Bachl, et al.

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.


page 4

page 8


Cocoa: Congestion Control Aware Queuing

Recent model-based congestion control algorithms such as BBR use repeate...

Optimizing Congestion Control Through Fair Queuing Detection

Low delay is an explicit requirement for applications such as cloud gami...

Fair Queuing Aware Congestion Control

Fair queuing is becoming increasingly prevalent in the internet and has ...

Poor Video Streaming Performance Explained (and Fixed)

HTTP-based video streaming is a key application on the Internet today, c...

Piece of CAKE: A Comprehensive Queue Management Solution for Home Gateways

The last several years has seen a renewed interest in smart queue manage...

New primitives for bounded degradation in network service

Certain new ascendant data center workloads can absorb some degradation ...

PAQMAN: A Principled Approach to Active Queue Management

Active Queue Management (AQM) aims to prevent bufferbloat and serial dro...

Please sign up or login with your details

Forgot password? Click here to reset