In the last decade, global cloud wide-area networks (WANs) have grown 10$\times$ in size due to the deployment of new network sites and datacenters, making it challenging for commercial optimization engines to solve the network traffic engineering (TE) problem within the temporal budget of a few minutes. In this work, we show that carefully designed deep learning models are key to accelerating the running time of intra-WAN TE systems for large deployments since deep learning is both massively parallel and it benefits from the wealth of historical traffic allocation data from production WANs. However, off-the-shelf deep learning methods fail to perform well on the TE task since they ignore the effects of network connectivity on flow allocations. They are also faced with a tractability challenge posed by the large problem scale of TE optimization. Moreover, neural networks do not have mechanisms to readily enforce hard constraints on model outputs (e.g., link capacity constraints). We tackle these challenges by designing a deep learning-based TE system -- Teal. First, Teal leverages graph neural networks (GNN) to faithfully capture connectivity and model network flows. Second, Teal devises a multi-agent reinforcement learning (RL) algorithm to process individual demands independently in parallel to lower the problem scale. Finally, Teal reduces link capacity violations and improves solution quality using the alternating direction method of multipliers (ADMM). We evaluate Teal on traffic matrices of a global commercial cloud provider and find that Teal computes near-optimal traffic allocations with a 59$\times$ speedup over state-of-the-art TE systems on a WAN topology of over 1,500 nodes.
翻译:在过去十年中,全球云广域网(WANs)由于部署新的网络站点和数据中心,其规模增加了10美元,使商业优化引擎在几分钟的时空预算内解决网络交通工程问题成为了挑战。在这项工作中,我们表明,精心设计的深层次学习模型对于加快广域网内部TE系统运行时间以进行大规模部署至关重要,因为深层次的学习是巨大的平行的,并且受益于生产网提供的大量历史交通分配数据。然而,由于低层次的深层次学习方法忽视了网络连通对流量分配的影响,因此在TE任务上表现不佳。此外,神经网络没有机制来方便地对模型产出(例如连接能力限制)施加硬性限制。我们通过设计一个深层次的基于学习的TE系统 -- -- Teal。 首先,Teal的平价网络(GNNN)无法忠实地捕捉到网络的连通性和模型流动。第二,Tealfal设计了网络连接性商业网络对流量的影响。Teopal-Teal-dealalalalalalalalalalalal-commogrational commal laction a laction acal rouplicks a laction a lax lax lax the lex lex lex lexal legal legal legal legal legal lection legal lemental legal lemental commodal commodal lemental legaldaldaldaldal lementaldal madaldaldal commildaldaldaldaldal commaxal max max maxaldaldaldaldal madaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldal commadal commadal commadal commadaldal commal commal commal commal commas commal commal comm