Congestion Control using Efficient Explicit Feedback

Qazi, Ihsan Ayyub; Andrew, Lachlan L. H.; Znati, Taieb

doi:10.1109/infcom.2009.5061901

Cited by 28 publications

(19 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is in contrast with currently used TCP-based logic, where flows compete for capacity in a never ending fight for resources without ever reaching a stable state or full resource utilization. All designs that tried to improve this situation did so by utilizing feedback from the network requiring the network to change -routers to add functionality [19], [1]. The presented system is the first as far as authors are aware of that provides the capability for network flows to cooperate in achieving optimal network utilization without the need for any support from the network -thus usable on the currently deployed infrastructure.…”

Section: Figmentioning

confidence: 99%

Novel methods of utilizing Jitter for Network Congestion Control

Klimek¹,

Čajkovský²,

Jakab³

2013

AIP

View full text Add to dashboard Cite

This paper proposes a novel paradigm for network congestion control. Instead of perpetual conflict as in TCP, a proof-of-concept first-ever protocol enabling inter-flow communication without infrastructure support thru a side channel constructed on generic FIFO queue behaviour is presented. This enables independent flows passing thru the same bottleneck queue to communicate and achieve fair capacity sharing and a stable equilibrium state in a rapid fashion.

show abstract

Section: Figmentioning

confidence: 99%

Novel methods of utilizing Jitter for Network Congestion Control

Klimek¹,

Čajkovský²,

Jakab³

2013

AIP

View full text Add to dashboard Cite

show abstract

“…Approaches such as VCP [31], MLCP [32], BMCC [33], XCP [13], RCP [34], and rate feedback in Quick-Start [12] are based on intermediate routers providing more extensive feedback, but more importantly are not meant to be submissive to other flows.…”

Section: Related Workmentioning

confidence: 99%

NF-TCP: A Network Friendly TCP Variant for Background Delay-Insensitive Applications

Arumaithurai

Ramakrishnan

2011

Networking 2011

View full text Add to dashboard Cite

Abstract. Delay-insensitive applications, such as P2P file sharing, generate substantial amounts of traffic and compete with other applications on an equal footing when using TCP. Further, to optimize throughput, such applications typically open multiple connections. This results in unfair and potentially poor service for applications that have stringent performance objectives (including sensitivity to delay and loss). In this paper, we propose NF-TCP, a TCP variant for P2P and similar delay-insensitive applications that can afford to have communication in the "background". NF-TCP aims to be submissive to delay-sensitive applications under congestion. A major component of NF-TCP is to integrate measurement as an integral component of the congestion control framework. This enables the transport to exploit available bandwidth, so that it can aggressively utilize spare capacity.We implemented NF-TCP on Linux and ns-2. Our evaluations of the NF-TCP Linux implementation on ns-2 show that NF-TCP outperforms other network friendly approaches (e.g., LEDBAT, TCP-LP and RAPID). NF-TCP achieves high utilization, fair bandwidth allocation among NF-TCP flows and maintains a small average queue. Our evaluations further demonstrate that with NF-TCP, the available bandwidth can be efficiently utilized.

show abstract

“…The use of explicit network feedback has been proposed to address the limitation of end-to-end schemes, such as TCP+AQM/ECN proposals [11,12] and XCP [13]. Some recent research [14][15][16] Performance as a function of the RTT variation load factor (the relative ratio of demand and capacity) as a signal of congestion. It only needs several bits such as the existing 2 ECN bits to achieve near-optimal bandwidth utilization and rate of convergence.…”

Section: B Congestion Control Algorithmmentioning

confidence: 99%

Towards zero loss for TCP in wireless networks

Chen

Tan

Liu

et al. 2009

2009 IEEE 28th International Performance Computing and Communications Conference

View full text Add to dashboard Cite

We propose a novel dynamic network coding retransmission scheme which can effectively mask packet losses and have a quite low decoding delay. By using network coding, we reduce the retransmission waiting time, and by using the implicit information of seen scheme, we acquire the exact number of packets the receiver needs for decoding packets. As our scheme does not require or estimate the loss rate to send redundancies in a constant rate, it is more practical to be implemented in a real system. Furthermore, we incorporate network coding with a load factor based congestion control algorithm which is easy and efficient to be implemented in practical systems. Simulation results show that our scheme significantly outperforms the previous coding approach in reducing decoding delay without sacrificing throughput. It achieves the near-zero congestion loss and "zero" error loss in wireless networks, can be easily and effectively implemented in the practical system. Keywords-network coding; packet loss; decoding delay; TCPI. 65978-1-4244-5736-6/09/$26.00 ©2009 IEEE

show abstract

Congestion Control using Efficient Explicit Feedback

Cited by 28 publications

References 25 publications

Novel methods of utilizing Jitter for Network Congestion Control

Novel methods of utilizing Jitter for Network Congestion Control

NF-TCP: A Network Friendly TCP Variant for Background Delay-Insensitive Applications

Towards zero loss for TCP in wireless networks

Contact Info

Product

Resources

About