LFQ: Online Learning of Per-flow Queuing Policies using Deep Reinforcement Learning
Authors:
- 16 November 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 417-420
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.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Cocoa2019
- Who will Save the Internet from the Congestion Control Revolution?2019
- Interactions between Congestion Control Algorithms2019
- Rax: Deep Reinforcement Learning for Congestion Control2019
- DeePCCI2019
- Design of an active queue management technique based on neural networks for congestion control2017
- BBR: Congestion-Based Congestion ControlQueue, 2016