Impact of cross traffic burstiness on the packet-scale paradigm

Lovewell, Rebecca; Kaur, Jasleen

doi:10.1109/lanman.2011.6076924

Cited by 2 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…cause fierce bandwidth competitions among flows, which we call bandwidth turbulence. The reasons [27,29] and effects [29][30][31] of Internet bursty flows have been studied for many years. Wu et al [32] established an influence propagation model of Internet bursty flow to describe the impacts of bursty flow on its neighbours.…”

mentioning

confidence: 99%

Bandwidth turbulence control based on flow community structure in the Internet

2016

EPL

View full text Add to dashboard Cite

Bursty flows vary rapidly in short period of time, and cause fierce bandwidth turbulence in the Internet. In this letter, we model the flow bandwidth turbulence process by constructing a flow interaction network (FIN network), with nodes representing flows and edges denoting bandwidth interactions among them. To restrain the bandwidth turbulence in FIN networks, an immune control strategy based on flow community structure is proposed. Flows in community boundary positions are immunized to cut off the inter-community turbulence spreading. By applying this control strategy in the first- and the second-level flow communities separately, 97.2% flows can effectively avoid bandwidth variations by immunizing 21% flows, and the average bandwidth variation degree reaches near zero. To achieve a similar result, about 70%–90% immune flows are needed with targeted control strategy based on flow degrees and random control strategy. Moreover, simulation results showed that the control effect of the proposed strategy improves significantly if the immune flow number is relatively smaller in each control step.

show abstract

mentioning

confidence: 99%

Bandwidth turbulence control based on flow community structure in the Internet

2016

EPL

View full text Add to dashboard Cite

show abstract

TCP Rapid: From theory to practice

Yin

Kaur

Smith

2017

IEEE INFOCOM 2017 - IEEE Conference on Computer Communications

Self Cite

View full text Add to dashboard Cite

Delay and bandwidth-based alternatives to TCP congestion-control have been around for nearly three decades and have seen a recent surge in interest. However, such designs have faced significant resistance in being deployed on a wide-scale across the Internet-this has been mostly due to serious concerns about noise in delay measurements, pacing inter-packet gaps, and required changes to the standard TCP stack. With the advent of high-speed networking, some of these concerns become even more significant. This thesis considers Rapid, a recent proposal for ultra-high speed congestion control, which perhaps stretches each of these challenges to the greatest extent. Rapid adopts a framework of continuous finescale bandwidth probing and rate adapting. It requires finely-controlled inter-packet gaps, high-precision timestamping of received packets, and reliance on fine-scale changes in inter-packet gaps. While simulationbased evaluations of Rapid show that it has outstanding performance gains along several important dimensions, these will not translate to the real-world unless the above challenges are addressed. This thesis identifies the key challenges TCP Rapid faces on real high-speed networks, including deployability in standard protocol stacks, precise inter-packet gap creation, achieving robust bandwidth estimation in the presence of noise, and a stability/adaptability trade-off. A Linux implementation of Rapid is designed and developed after carefully considering each of these challenges. The evaluations on a 10Gbps testbed confirm that the implementation can indeed achieve the claimed performance gains, and that it would not have been possible unless each of the above challenges was addressed.

show abstract

Impact of cross traffic burstiness on the packet-scale paradigm

Cited by 2 publications

References 6 publications

Bandwidth turbulence control based on flow community structure in the Internet

Bandwidth turbulence control based on flow community structure in the Internet

TCP Rapid: From theory to practice

Contact Info

Product

Resources

About