arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.02735cs.NIcs.LG
收藏

LFQ:使用深度强化学习在线学习逐流策略

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

Technische Universität Wien(维也纳工业大学)

Maximilian Bachl, Joachim Fabini, Tanja Zseby

摘要:

不同的、不兼容的拥塞控制算法数量的增加导致了公平排队部署的增加。公平排队隔离每个网络流,并且因此即使流的拥塞控制不是固有公平的,也可以保证每个流的公平性。到目前为止,公平排队系统中的每个队列要么有一个固定的、静态的最大长度,要么由一个主动队列管理(AQM)算法(如CoDel)管理。在本文中,我们设计了一个主动队列管理机制(学习公平Qdisc(LFQ)),动态学习的最佳缓冲区大小为每个流根据一个指定的奖励函数在线。我们表明,我们的基于深度学习的算法可以动态分配最佳队列大小,每个流取决于其拥塞控制,延迟和带宽。与竞争公平的AQM队列管理器相比,它提供了显着更小的队列,同时实现相同或更高的吞吐量。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑