LFQ: Online Learning of Per-flow Queuing Policies using Deep Reinforcement Learning
Authors:
Preprint
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 (Fair Learning 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:
- Deep Reinforcement Learning Based Active Queue Management for IoT NetworksJournal of Network and Systems Management, 2021
- Flow length and size distributions in campus Internet trafficComputer Communications, 2021
- Cocoa2019
- Who will Save the Internet from the Congestion Control Revolution?2019
- Toward Low-Latency and Ultra-Reliable Virtual RealityIEEE Network, 2018
- The Flow Queue CoDel Packet Scheduler and Active Queue Management Algorithm2018
- BBR: Congestion-Based Congestion ControlQueue, 2016