CNS Core: Large: Collaborative Research: Network Design Automation

CNS 核心：大型：协作研究：网络设计自动化

• 批准号: 1901510
• 负责人: George Varghese
• 金额: $ 199.94万
• 依托单位: University of California-Los Angeles
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-07-01 至 2024-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1901510&HistoricalAwards=false
• 关键词: CNS; Core; Large; Collaborative; Research

When we use Office365, Amazon, or Facebook, we access a world of rich services via a network. Network reliability is paramount for business, science, and government because downtime affects productivity, economic output, and social communication. However, reliability is difficult to achieve in the face of component failure, manual configuration, and the stringent economics of the Information Technology (IT) industry. This project will take first steps towards creating a new field of inquiry, Network Design Automation (NDA). NDA seeks to create computer-aided design (CAD) tools that reduce design effort and increase reliability based on a scientific understanding of network structure. NDA is inspired by Electronic Design Automation (EDA), a $7 billion industry that underpins the $100 billion chip industry, and is a vibrant intellectual discipline in its own right.NDA will verify networks using formal methods but also broaden the agenda to debugging networked systems and to other specialized networks such as rural networks and content distribution networks. Specific new tasks include tying application performance to network problems using machine learning, understanding failure logs using Natural Language Processing, creating more controllable routers inspired by hardware boundary scan ideas, rural network design using constraint satisfaction, network scripting to lower the barriers for operators, and data mining to find configuration bugs without a specification. Networks have unique challenges including heterogeneity, management complexity, rate of evolution (new data centers and service rollouts), and high availability needs. Besides a consistent focus on using algorithm search, we will leverage data mining, machine learning, Natural Language Processing, and hardware test approaches. NDA will not merely reuse existing mechanisms, but will exploit domain-specific insights about the structure of modern networks to invent new and scalable approaches.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

当我们使用Google 365、亚马逊或Facebook时，我们通过网络访问了一个丰富的服务世界。网络可靠性对商业、科学和政府至关重要，因为停机会影响生产力、经济产出和社会沟通。然而，面对组件故障、手动配置和信息技术（IT）行业的严格经济性，可靠性难以实现。该项目将朝着创建一个新的调查领域，网络设计自动化（NDA）迈出第一步。 NDA旨在创建计算机辅助设计（CAD）工具，以减少设计工作并基于对网络结构的科学理解提高可靠性。NDA的灵感来自于电子设计自动化（EDA），EDA是一个价值70亿美元的产业，支撑着价值1000亿美元的芯片产业，本身就是一个充满活力的知识学科。NDA将使用正式的方法来验证网络，但也将扩展议程到调试联网系统和其他专业网络，如农村网络和内容分发网络。 具体的新任务包括使用机器学习将应用性能与网络问题联系起来，使用自然语言处理理解故障日志，受硬件边界扫描思想的启发创建更可控的路由器，使用约束满足的农村网络设计，降低运营商障碍的网络脚本，以及在没有规范的情况下发现配置错误的数据挖掘。网络面临着独特的挑战，包括异构性、管理复杂性、发展速度（新数据中心和服务推出）以及高可用性需求。除了始终专注于使用算法搜索之外，我们还将利用数据挖掘，机器学习，自然语言处理和硬件测试方法。 NDA不仅将重用现有的机制，而且将利用对现代网络结构的特定领域的见解来发明新的可扩展的方法。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

AutoARTS: Taxonomy, Insights and Tools for Root Cause Labelling of Incidents in Microsoft Azure

• 发表时间: 2023
• 作者: Pradeep Dogga;Chetan Bansal;Richard Costleigh;Gopinath Jayagopal;Suman Nath;Xuchao Zhang

Revelio: ML-Generated Debugging Queries for Finding Root Causes in Distributed Systems

Revelio：ML 生成的调试查询，用于查找分布式系统中的根本原因

• 发表时间: 2022
• 期刊: Proceedings of Machine Learning and Systems 4 (MLSys 2022
• 作者: Dogga, Pradeep;Narasimhan, Karthik;Sivaraman, Anirudh;Varghese, George
• 通讯作者: Varghese, George

A System-Wide Debugging Assistant Powered by Natural Language Processing

由自然语言处理提供支持的全系统调试助手

• DOI: 10.1145/3357223.3362701
• 发表时间: 2019
• 期刊: Proceedings of the ACM Symposium on Cloud Computing
• 作者: Dogga, Pradeep;Narasimhan, Karthik;Sivaraman, Anirudh;Netravali, Ravi
• 通讯作者: Netravali, Ravi

Campion: debugging router configuration differences

• DOI: 10.1145/3452296.3472925
• 发表时间: 2021-08
• 期刊: Proceedings of the 2021 ACM SIGCOMM 2021 Conference
• 作者: Alan Tang;S. Kakarla;Ryan Beckett;Ennan Zhai;Matt Brown;T. Millstein;Y. Tamir;G. Varghese

Finding Network Misconfigurations by Automatic Template Inference

• 发表时间: 2020
• 作者: S. Kakarla;Alan Tang;Ryan Beckett;Karthick Jayaraman;T. Millstein;Y. Tamir;G. Varghese