[网络领域顶会追踪系列#28][SIGCOMM'22]DeepQueueNet：实现具有数据包粒度可见性的可扩展和通用网络性能估计

本系列为个人论文阅读笔记，大多数应该是对顶会摘要的个人菜鸟翻译，旨在让感兴趣的朋友能快速浏览、获取信息。如有错误或心得，欢迎在评论区交流指正！

DeepQueueNet: Towards Scalable and Generalized Network Performance Estimation with Packet-level Visibility

作者单位：华为理论实验室、中关村实验室、香港中文大学、山东计算机科学中心（济南国家超算中心）、多伦多大学

背景

网络仿真器是网络操作员的必要工具，可以协助进行一些重要工作如容量规划、拓扑设计和参数调优。

挑战

著名的仿真器都基于离散事件仿真，并且他们的性能不随着现代网络的规模而扩展。近期，基于深度学习的技术被引入以解决规模扩展问题，但是，正如作者的实验证明，他们在仿真结果上有着较弱的可视性，并且不能在多种场景上通用。

工作

在本文中，作者将可扩展和通用的连续仿真技术与离散事件仿真结合，以在提供包级别的可视化的同时，实现高可扩展性。

作者从一个坚实的队列理论模型出发，小心地分辨出数学棘手的或计算昂贵的部分，并仅仅对它们使用深度神经网络（DNN）建模。

作者的方法，DeepQueueNet，结合了网络的先验知识，支持任意拓扑和设备流量管理机制（在给定充足的流量数据的情况下）。

实验

作者的实验表明DeepQueueNet实现了随着GPU数量近似线性的加速，并且在所有场景下，它对平均和99th RTT的估计准确性的表现优于现有的端到端性能估计器

原文摘要

Network simulators are an essential tool for network operators, and can assist important tasks such as capacity planning, topology design, and parameter tuning. Popular simulators are all based on discrete event simulation, and their performance does not scale with the size of modern networks. Recently, deep-learning-based techniques are introduced to solve the scalability problem, but, as we show with experiments, they have poor visibility in their simulation results, and cannot generalize to diverse scenarios. In this work, we combine scalable and generalized continuous simulation techniques with discrete event simulation to achieve high scalability, while providing packet-level visibility. We start from a solid queueing-theoretic modeling of modern networks, and carefully identify the mathematically-intractable or computationally-expensive parts, only which are then modeled using deep neural networks (DNN). Dubbed_DeepQueueNet_, our approach combines prior knowledge of networks, and supports arbitrary topology and device traffic management mechanisms (given sufficient training data). Our extensive experiments show that DeepQueueNet achieves near-linear speedup in the number of GPUs, and its estimation accuracy for average and 99th percentile round-trip time outperforms existing end-to-end DNN-based performance estimators in all scenarios.