A hop by hop rate-based congestion control scheme

Mishra, P.P.; Kanakia, Hemant

doi:10.1145/144179.144254

Cited by 97 publications

(65 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Upward propagation of the congestion state can occur in the network using the hop-by-hop flow-control scheme, such as the back-pressure [12, pp. 506-507] and others [13]. By the backpressure scheme, for instance, the congestion state propagates backward from the congested node to the multicast sources through the back-pressure signal.…”

Section: A2 Link Congestion Marking Dependencymentioning

confidence: 99%

Markov-Chain Modeling for Multicast Signaling Delay Analysis

Zhang¹,

Shin

2004

IEEE/ACM Trans. Networking

View full text Add to dashboard Cite

Abstract-Feedback signaling plays a key role in flow control because the traffic source relies on the signaling information to make correct and timely flow-control decisions. However, it is difficult to design an efficient signaling algorithm since a signaling message can tolerate neither error nor latency. Multicast flow-control signaling imposes two additional challenges: scalability and feedback synchronization. Previous research on multicast signaling has mainly focused on the development of algorithms without analyzing their delay performance. To remedy this deficiency, we have previously developed a binary-tree model and an independent-marking statistical model for multicast-signaling delay analysis. This paper considers a general scenario where the congestion markings at different links are dependent-a more accurate but complex case. Specifically, we develop a Markov-chain model defined by the link-marking state on each path in the multicast tree. The Markov chain can not only capture link-marking dependencies, but also yield a tractable analytical model. We also develop a Markov-chain dependency-degree model to evaluate all possible Markov-chain dependency degrees without any prior knowledge of them. Using the above two models, we derive the general probability distributions of each path becoming the multicast-tree bottleneck. Also derived are the first and second moments of multicast signaling delays. The proposed Markov chain is also shown to asymptotically reach an equilibrium, and its limiting distribution converges to the marginal link-marking probabilities when the Markov chain is irreducible. Applying the two models, we analyze and contrast the delay scalability of two representative multicast signaling protocols: Soft-Synchronization Protocol (SSP) and Hop-By-Hop (HBH) algorithms.

show abstract

Section: A2 Link Congestion Marking Dependencymentioning

confidence: 99%

Markov-Chain Modeling for Multicast Signaling Delay Analysis

Zhang¹,

Shin

2004

IEEE/ACM Trans. Networking

View full text Add to dashboard Cite

show abstract

“…We refer to this value as the setpoint. We refer the reader to [MK92;MKT93] for greater details about the control mechanism.…”

Section: Rate Adaptationmentioning

confidence: 99%

“…In this scheme it is assumed that all packets belonging to the same aggregated group are queued together at network switches and hosts and sent out in a First-In-First-Out manner. A rate control mechanism is enforced in the network layer protocol at the host and switches as described in [MK92;MKT93]. This control mechanism forces packets to be sent out from the common queue (at the host/switch) to the downstream switch at a particular rate.…”

Section: Rate Adaptationmentioning

confidence: 99%

“…First, we discuss how a rate based hop by hop (HBH) congestion control scheme, previously proposed by us to control data traffic [MK92;MKT93], may be modified to control the :How of image traffic. We compare the performance of the modified HBH scheme as measured by the average transfer times with an unachievable lower bound on the transfer time and show that the average transfer times achieved with the HBH mechanism are within 15-30% of the lower bound.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Study of Bandwidth Allocation Strategies for Interactive Image Applications

Mishra

Tripathi

1995

Computer Networks, Architecture and Applications

Self Cite

View full text Add to dashboard Cite

Image applications are expected to consume a significant portion of the bandwidth of future integrated service networks. In this paper, we examine the effectiveness of various bandwidth allocation mechanisms for this class of applications. First, we describe how a rate based hop by hop (HBH) congestion control scheme, proposed previously by us for controlling data traffic, may be modified to control the flow of image traffic. The performance of the modified HBH scheme as measured by the average image transfer times is shown to be within 15-30% of an unachievable lower bound. We also compare the effectiveness of the HBH scheme with a hierarchical round robin (HRR) scheme that reserves bandwidth before commencing each image transfer. Our results indicate that the likelihood of exceeding a desired transfer time requirement with the HBH scheme is lower than the blocking probability with the HRR scheme. Moreover, the average transfer times achieved with the HBH scheme are much lower. However, the variation of the transfer time is very small with the HRR scheme. We also show that the HBH scheme may be used to effectively trade transfer time vs image quality.

show abstract

“…For example, [29] proposes to distinguish the interpretation of the backpressure/pause message for di¤erent tra¢ c classes. There is also a signi…cant amount of work done on ATM (Asynchronous Transfer Mode) based hop-by-hop ‡ow control as in [60] and [52]. However, most of this work is based on negotiating transmission rates between the congested node and its upstream neighbors.…”

Section: Chapter 5 Interaction Of Ethernet and Tcp Congestion Controlmentioning

confidence: 99%

Quality of service modeling and analysis for carrier ethernet

Malhotra¹

View full text Add to dashboard Cite

A hop by hop rate-based congestion control scheme

Cited by 97 publications

References 15 publications

Markov-Chain Modeling for Multicast Signaling Delay Analysis

Markov-Chain Modeling for Multicast Signaling Delay Analysis

A Study of Bandwidth Allocation Strategies for Interactive Image Applications

Quality of service modeling and analysis for carrier ethernet

Contact Info

Product

Resources

About