arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.09337cs.LGcs.AIcs.NI
收藏

数据中心拥塞控制的强化学习

Reinforcement Learning for Datacenter Congestion Control

Nvidia Research(英伟达研究院)

Chen Tessler, Yuval Shpigelman, Gal Dalal, Amit Mandelbaum, Doron Haritan Kazakov, Benjamin Fuhrer, Gal Chechik, Shie Mannor

摘要:

我们使用强化学习(RL)来处理网络拥塞控制的任务。成功的拥塞控制算法可以显著改善延迟和整体网络吞吐量。直到今天,还没有这样的基于学习的算法在这一领域显示出实际的潜力。显然,最近最流行的部署依赖于基于规则的算法,这些算法在预定的基准集上进行测试。因此,这些理论不能很好地推广到新出现的场景。首先,我们设计了一个基于RL的算法,其目的是推广到现实世界的数据中心网络的不同配置。我们克服了部分可观测性,非平稳性和多目标性等挑战。我们进一步提出了一个策略梯度算法,利用奖励函数的解析结构来近似其导数并提高稳定性。我们表明,该方案优于其他流行的RL方法,并推广到训练过程中没有看到的场景。我们的实验,在一个现实的模拟器,模拟通信网络的行为,表现出改善的性能,同时对多个考虑的指标相比,今天部署在真正的网络中心的流行算法。我们的算法正在产品化,以取代世界上一些最大的物流中心的物流。

英文摘要:

We approach the task of network congestion control in datacenters using Reinforcement Learning (RL). Successful congestion control algorithms can dramatically improve latency and overall network throughput. Until today, no such learning-based algorithms have shown practical potential in this domain. Evidently, the most popular recent deployments rely on rule-based heuristics that are tested on a predetermined set of benchmarks. Consequently, these heuristics do not generalize well to newly-seen scenarios. Contrarily, we devise an RL-based algorithm with the aim of generalizing to different configurations of real-world datacenter networks. We overcome challenges such as partial-observability, non-stationarity, and multi-objectiveness. We further propose a policy gradient algorithm that leverages the analytical structure of the reward function to approximate its derivative and improve stability. We show that this scheme outperforms alternative popular RL approaches, and generalizes to scenarios that were not seen during training. Our experiments, conducted on a realistic simulator that emulates communication networks' behavior, exhibit improved performance concurrently on the multiple considered metrics compared to the popular algorithms deployed today in real datacenters. Our algorithm is being productized to replace heuristics in some of the largest datacenters in the world.

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。

↑