Collaborative Research: CNS: Medium: Scalable Learning from Distributed Data for Wireless Network Management

合作研究：CNS：媒介：无线网络管理的分布式数据可扩展学习

• 批准号: 2106214
• 负责人: Vyas Sekar
• 金额: $ 20万
• 依托单位: Carnegie-Mellon University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-10-01 至 2025-09-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2106214&HistoricalAwards=false
• 关键词: Collaborative; Research; CNS; Medium; Scalable

The transition to 5G is expected to witness not only an emergence of new applications such as mobile augmented and virtual reality, but also opens up the attack surface to both known, and previously unknown threats. Thus, wireless networks of the future will need better control and management at different temporal and traffic aggregation granularities (e.g., how to allocate spectrum, how to quarantine distributed attacks etc.). This project aims to develop scalable, machine learning based analytics on the data from a large set of geographically distributed wireless core network entities such as base stations. The research will enable new approaches for: (a) compressing the raw data via novel summaries and sketches, that reduce overhead while simultaneously enabling highly accurate scalable analytics (b) scalable yet highly flexible distributed learning approaches that are built upon the emerging federated learning paradigm and (c) flexible allocation of bandwidth to support the control plane analytics that minimizes the impact on the data plane. The proposed research outcomes will be systems, algorithms, and data analytics workflows that will inform the design and management of next generation critical wireless infrastructures. The approaches developed will enable ISPs to better apportion resources and enable better performance for emerging augmented reality applications for societal benefit (e.g., disaster response and management). In addition, the approaches can enable the discovery and profiling of new threats, which will have significant implications on national security. The proposed education activities are expected to provide students with a comprehensive training in networking, security, system building, and data science. Thus, there is significant potential for broader impact in terms of contributions to workforce development in an area of national need.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.

向5G的过渡预计不仅会见证移动增强和虚拟现实等新应用的出现，还会打开攻击面，既可以攻击已知的威胁，也可以攻击以前未知的威胁。因此，未来的无线网络将需要在不同的时间和流量聚合粒度(例如，如何分配频谱、如何隔离分布式攻击等)上更好地控制和管理。该项目旨在开发可扩展的、基于机器学习的分析，基于来自大量地理分布的无线核心网络实体(如基站)的数据。这项研究将为以下方面提供新的方法：(A)通过新颖的摘要和草图压缩原始数据，从而减少开销，同时实现高精度的可扩展分析；(B)基于新兴的联合学习范式构建的可扩展但高度灵活的分布式学习方法；以及(C)灵活分配带宽，以支持控制平面分析，从而将对数据平面的影响降至最低。建议的研究成果将是系统、算法和数据分析工作流，将为下一代关键无线基础设施的设计和管理提供信息。开发的方法将使互联网服务提供商能够更好地分配资源，并使新出现的增强现实应用程序具有更好的性能，从而造福于社会利益(例如，灾害应对和管理)。此外，这些方法可以发现和剖析新的威胁，这将对国家安全产生重大影响。拟议的教育活动预计将为学生提供网络、安全、系统建设和数据科学方面的全面培训。因此，在国家需求领域对劳动力发展的贡献方面，有很大的潜力产生更广泛的影响。这一奖项反映了NSF的法定使命，并通过使用基金会的智力优势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

Sketchovsky: Enabling Ensembles of Sketches on Programmable Switches

• 发表时间: 2023
• 作者: Hun Namkung;Zaoxing Liu;Daehyeok Kim;Vyas Sekar;P. Steenkiste

Enabling Efficient and General Subpopulation Analytics In Multidimensional Data Streams In VLDB 2022

在 VLDB 2022 的多维数据流中实现高效、通用的子群体分析

• 发表时间: 2022
• 期刊: PVLDB
• 作者: Manousis, Antonis