NeTS: Medium: Collaborative Research: Towards Versatile and Programmable Measurement Architecture for Future Networks

该奖项是根据2009年美国复苏和再投资法案（公法111-5）资助的。流量测量是网络运行、管理和安全的核心。然而，对衡量的支持并不是原始互联网架构的一个组成部分。该项目旨在开发一种可编程的测量架构，该架构具有足够的通用性，能够支持当前和未来的测量需求，适应动态网络条件，模块化/轻量化，并可扩展到高链路速度。该项目提出了一种新的流抽象模块和查询语言，可以指定任意的流量子群体的统计数据收集。将开发对这些查询进行编码的有效数据结构。该团队还致力于确定一组核心的数据流和采样原语，这些原语可以组合在一起以满足大多数查询。这些核心原语集的有效硬件实现将构成基本的测量模块，可以很容易地重新配置，以测量在不同的所需粒度的流量。将进行测量应用案例研究，以评估和展示拟议方法的能力。该项目具有很大的潜力，在指导设计一个干净的石板测量仪器，为未来的互联网。它将为研究生和本科生提供跨越多个学科的培训，从基础统计理论，算法设计到硬件实现。研究结果（包括查询语言和底层数据结构、采样/流算法和硬件构建模块）将通过出版物、特邀讲座/教程和开源软件分发广泛传播。

This award is funded under the American Recovery and Reinvestment Act of 2009 (Public Law 111-5). Traffic measurement is central to network operation, management, and security. Yet, support for measurement was not an integral part of the original Internet architecture. This project aims to develop a programmable measurement architecture that is versatile enough to support current and future measurement needs, adaptable to dynamic network conditions, modular/lightweight, and scalable to high link speeds. This project proposes a new flow abstraction module and query language that can specify arbitrary traffic sub-populations for statistics collection. Efficient data structures to encode these queries will be developed. The team also strives to identify a core set of data streaming and sampling primitives that can be composed together to satisfy most of the queries. Efficient hardware implementation for these core set of primitives will constitute the basic measurement modules that can be easily reconfigured to measure traffic at different desired granularity. Measurement application case studies will be carried out to evaluate and showcase the capabilities of the proposed approach. This project has great potential in guiding the design of a clean-slate measurement instrumentation for future Internet. It will provide both graduate and undergraduate students with training that span multiple disciplines, from fundamental statistical theory, algorithm design, to hardware implementation. The results (including the query language and underlying data structures, sampling/streaming algorithms, and hardware building blocks) will be broadly disseminated through publications, invited talks/tutorials, and open-sourcing software distribution.