NeTS-NBD: Distributed Congestion Control for Heterogeneous Networks

NeTS-NBD：异构网络的分布式拥塞控制

• 批准号: 0519442
• 负责人: Dmitri Loguinov
• 金额: $ 30万
• 依托单位: Texas A&M Engineering Experiment Station
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2005
• 资助国家: 美国
• 起止时间: 2005-09-01 至 2009-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0519442&HistoricalAwards=false
• 关键词: NeTS; NBD; Distributed; Congestion; Control

In the light of TCP's scalability issues in high bandwidth-delay networks, explicit-feedback congestion control has gained renewed interest in the last several years. Sometimes referred to as Active Queue Management (AQM) congestion control, these algorithms rely on the routers to provide the various types of congestion feedback including changes to the congestion window, packet loss, single-bit congestion indication, queuing delay, and link prices. This information helps end-flows converge their sending rates to some social optimum and achieve a certain optimization objective. Unlike some of the largely ineffective AQM aimed at improving the performance of TCP, properly designed explicit congestion control promises to provide scalability to arbitrary bandwidth (i.e., terabits and petabits per second), tunable link utilization, low delay, zero loss, oscillation-free steady state, and exponential convergence to fairness/efficiency. Such algorithms, once deployed successfully in the Internet, may remain in service for many years to come. This proposal does not aim to settle the debate of whether or when explicit congestion control can/will be adopted by the Internet, but to explore the various properties of the existing AQM methods (such as XCP, RCP, MKC, AVQ, and MaxNet), propose a new controller that improves the performance of existing approaches in highly heterogeneous network conditions, and evaluate its performance in a network of software and hardware routers. Broader Impact: Aside from theoretical contributions to delayed and discontinuous stability analysis of congestion control, this project will deliver a low-overhead implementation of the studied methods, educate graduate and undergraduate students, and disseminate the various findings to the public.

鉴于TCP在高带宽延迟网络中的可伸缩性问题，显式反馈拥塞控制在过去几年中重新引起了人们的兴趣。这些算法有时被称为主动队列管理（AQM）拥塞控制，它们依赖于路由器提供各种类型的拥塞反馈，包括对拥塞窗口的更改、数据包丢失、单比特拥塞指示、排队延迟和链路价格。这些信息有助于终端流将其发送速率收敛到某个社会最优，从而实现一定的优化目标。与一些旨在提高TCP性能的大部分无效的AQM不同，适当设计的显式拥塞控制承诺提供任意带宽（即每秒太比特和千兆比特）的可扩展性，可调的链路利用率，低延迟，零损失，无振荡稳定状态以及公平/效率的指数收敛。这样的算法，一旦在互联网上成功部署，可能会在未来的许多年里继续使用。本提案的目的不是解决互联网是否或何时可以/将采用显式拥塞控制的争论，而是探索现有AQM方法（如XCP， RCP， MKC， AVQ和MaxNet）的各种特性，提出一种新的控制器，提高现有方法在高度异构网络条件下的性能，并评估其在软件和硬件路由器网络中的性能。更广泛的影响：除了对拥塞控制的延迟和不连续稳定性分析的理论贡献外，该项目将提供所研究方法的低开销实施，教育研究生和本科生，并向公众传播各种发现。