Owl: Congestion Control with Partially Invisible Networks via Reinforcement Learning
Owl: Congestion Control with Partially Invisible Networks via Reinforcement Learning
复制标题
DOI：
10.1109/infocom42981.2021.9488851
复制
发表时间：
2021-05
期刊：
影响因子：
--
通讯作者：
Alessio Sacco;Matteo Flocco;Flavio Esposito;G. Marchetto
中科院分区：
文献类型：
--
作者：
Alessio Sacco;Matteo Flocco;Flavio Esposito;G. Marchetto
多年来对传输协议的研究并没有解决网内拥塞控制和端到端拥塞控制之间的矛盾。这一争论是由于不同网络场景中的条件和假设的差异，例如，蜂窝网络与数据中心网络。最近，社区已经提出了一些由机器学习驱动的传输协议，但仅限于端到端的approaches.In本文中，我们提出了猫头鹰，基于强化学习的传输协议，其目标是选择合适的拥塞窗口学习从端到端的功能和网络信号，当可用的。我们表明，我们的解决方案收敛到一个公平的资源分配后的学习开销。我们的内核实现部署在仿真和大规模虚拟网络测试平台上，优于所有基于端到端或网络内拥塞控制的基准解决方案。
Years of research on transport protocols have not solved the tussle between in-network and end-to-end congestion control. This debate is due to the variance of conditions and assumptions in different network scenarios, e.g., cellular versus data center networks. Recently, the community has proposed a few transport protocols driven by machine learning, nonetheless limited to end-to-end approaches.In this paper, we present Owl, a transport protocol based on reinforcement learning, whose goal is to select the proper congestion window learning from end-to-end features and network signals, when available. We show that our solution converges to a fair resource allocation after the learning overhead. Our kernel implementation, deployed over emulated and large scale virtual network testbeds, outperforms all benchmark solutions based on end-to-end or in-network congestion control.