Brian Neil Levine and J. J. Garcia-Luna-Aceves. A comparison of reliable multicast protocols. Multimedia Systems, 6(5):334-348, 1998.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....from every receiver for every packet sent. A lost packet is detected when an ACK fails to arrive from one or more receivers. When a loss is detected, the packet is retransmitted and the sender again waits for an ACK from every receiver. Such sender initiated protocols suffer from ACK implosion [33, 34], in which a flood of acknowledgments arrives in response to each packet sent, as shown in Figure 12. Increasing amounts of network bandwidth and processing time are consumed as the number of receivers in the group increases, which limits the group size that such protocols can accommodate. ....

B.N. Levine and J.J. Garcia-Luna-Aceves, "A Comparison of Reliable Multicast Protocols," ACM Multimedia Systems J. 6 (5), 1998, pp. 334--338, <http://www.cse.ucsc.edu/research/ ccrg/publications/brian.mmsj.ps.gz>.

....queuing delay in detail and neglect feedback processing. They concluded that local recovery techniques and parity packets outperform other approaches. Our analysis is based on the delay analysis of Yamamoto et al. 7] and on the basic analytical work of Pingali et al. 10] and Levine et al. [11]. Pingali et al. have done the first comparative analysis of reliable multicast protocols. They have compared the processing requirements of flat protocol classes. Levine et al. have extended this work to the class of ring and tree based approaches. To our knowledge, our work is the first ....

....results with simulation studies. 3 Protocol Classification and Description In this section we briefly describe and classify the reliable multicast protocols analyzed and simulated in this paper. A more detailed and more general description for some of these classes can be found in [10] [11] and [9] The first considered protocol class is a receiver initiated protocol. Receiverinitiated protocols return only negative acknowledgments (NACKs) from receivers to the sender instead of positive acknowledgements (ACKs) When a receiver detects an error, e.g. by a wrong checksum, a skip in ....

[Article contains additional citation context not shown here]

Levine, B., Garcia-Luna-Aceves, J.: A comparison of reliable multicast protocols. Multimedia Systems 6 (1998) 334--348

....A main advantage that multicast based solutions have over client server solutions is their often inherent decentralized nature. This makes these solutions particularly attractive for large scale networks, except that building scalable reliable multicasting schemes is notoriously difficult [4], 5] Fortunately, matters improve when dealing with probabilistic schemes in which no hard guarantees are given concerning the delivery of a multicast message. If a multicast message is required to be only eventually delivered with a high probability to all current group members, it appears that ....

Brian Neil Levine and Jose J. Garcia-Luna-Aceves, "A comparison of reliable multicast protocols," Multimedia Systems, vol. 6, no. 5, pp. 334--348, 1998.

....communication identifies a body of research whose goal is to provide mechanisms for reliable communication among a group of possibly remote processes, and in addition to guarantee some degree of ordering and atomicity [5] of message delivery. Under this umbrella fall reliable multicast protocols [10, 11] as well as more complex systems such as Isis [2] and Horus [20] In contrast to these goals, the main purpose of contentbased publish subscribe middleware is to distribute messages (i.e. events) to all the interested parties based on their content and to do so in a scalable and e#cient way. ....

B. Levine and J. Garcia-Luna-Aceves. A comparison of reliable multicast protocols. ACM Multimedia Systems Journal, 6(5):334--348, August 1998.

....However, it also increases duplicate packets on the topology by nearly 10 . V. RELATED WORK A large number of research proposals have addressed reliable delivery for multicast data, most notably in the context of network layer multicast. A comparative survey of these protocols is given in [12] and [22] In SRM [7] receivers send NAKs to the source to indicate missing data packets. Each such NAK is multicast to the entire group and is used to suppress NAKs from other receivers that did not get the same packet. In this approach, however, a few receivers behind a lossy link can incur a ....

B. Levine and J. Garcia-Luna-Aceves. A comparison of reliable multicast protocols. Multimedia Systems Journal, 6(5), Aug. 1998.

....build a hierarchy of subgroups and localize the error recovery. Assumption 4 describes a generic scheme inside each subgroup: proxy based error recovery with multicast retransmissions. There are many other available options very well summarized in [9] analytically compared in a number of studies [22, 25, 12]. Details of feedback and congestion control are ignored here. Our performance metrics capture the total transmissions needed to deliver a packet correctly to all members. If there is no loss, there should be only one transmission per packet. If there are losses, there are extra retransmissions ....

....1 to reliably deliver a single packet to the entire group, or for the proxy of Figure 2 to reliably deliver a packet to the entire subgroup. 3. 1 The E[M] Measure E[M] is an important measure, which first appeared in [1] and ever since has been used in most analytical work on Reliable Multicast [18, 20, 19, 22, 25, 12]. n l pn pl Figure 2. Inside a subgroup E[M] is defined to be the expected number of times that a packet should be multicast (original transmission retransmissions) by the source, until all group members receive it correctly, at least once. It depends on the shape of the tree and the link ....

B.N. Levine and J.J. Garcia-Luna-Aceves, "A Comparison of Reliable Multicast Protocols", in ACM Multimedia Systems Journal, August 1998

....reliable multicast, filtered layered multicast, as well as other security concerns. 7.2. 1 Reliable Multicast Although the original model for multicasting was based on the best e#ort unreliable delivery model of UDP, there has been considerable interest in developing a reliable multicast model [100, 101, 102, 103, 104]. Reliable multicast is especially applicable for areas such as content distribution networks (CDN) Both of the proposed architectures are compatible with reliable multicasting schemes but with several caveats. First, a reliable multicast scheme implies that per group monitoring is taking place ....

B. Levine and J. J. Garcia-Luna-Aceves, "A comparison of reliable multicast protocols," Multimedia Systems, vol. 6, no. 5, pp. 334--348, 1998.

.... These protocols are proven most scalable in terms of maximum throughput and end point bandwidth since they can ensure that the sender processing time is bounded by the number of the sender s children, which remains constant in their tree hierarchy regardless of the number of receivers [13][18] A limitation of the tree based reliable multicast protocols is that their best performance can be achieved when the ACK tree is close to its corresponding multicast routing tree. In such a high quality ACK tree, the underlying network layer correlation in terms of packet loss and delay is ....

B. N. Levine and J. J. Garcia-Luna-Aceves, "A Comparison of Reliable Multicast Protocols," ACM Multimedia Systems, 6, pp. 334-348, 1998

....5 reports the performance study and Section 6 concludes the paper. 2 Related work Extensive research has been conducted in the area of reliable multicast over the Internet [1, 3, 4, 7, 9, 10, 13, 15, 20, 21, 22] A summary of recent development of reliable multicast protocols can be found in [12]. The protocols can be broadly classified into four types, the ACK based protocols [20, 15] where all receivers send positive acknowledgments for each packet that they receive, the NAK based protocols [4, 7, 9, 10, 22] where the receivers monitor the sequence of packets they receive and send ....

B. N. Levine and J.J. Garcia-Luna-Aceves "A Comparison of Reliable Multicast Protocols." Multimedia Systems, 6:334--348, 1998.

....message delivery. A positive acknowledgment returned by a receiver con rms correct message delivery, whereas a negative acknowledgment asks for a message retransmission. It has been shown that tree based multicast protocols scale better than other multicast schemes suggested in the literature [1 4]. In tree based protocols, the members of a multicast group are organized in a so called ACK tree to overcome the well known acknowledgment implosion problem, i.e. overwhelming of the sender by a large number of positive (ACK) or negative (NAK) acknowledgment messages. Since acknowledgments are ....

....conclude our work with a brief summary. 2. Related Work Reliable multicast protocols were already analyzed in previous work. The rst work in this area was presented by Pingali et al. 7] They have compared the processing requirements of sender and receiver initiated protocols. Levine et al. [1] have extended this analysis to the class of ring and tree based approaches and showed that tree based approaches are superior. Bandwidth analysis of generic reliable multicast protocols were done by Kasera et al. 8] Nonnenmacher et al. 9] and Poo et al. 10] In [8] local recovery techniques ....

[Article contains additional citation context not shown here]

B. Levine and J. Garcia-Luna-Aceves, \A comparison of reliable multicast protocols," Multimedia Systems, vol. 6, no. 5, pp. 334-348, Sept. 1998.

....5 reports the performance study and Section 6 concludes the paper. 2 Related work Extensive research has been conducted in the area of reliable multicast over the Internet [1, 3, 4, 7, 9, 10, 14, 16, 24, 26, 27] A summary of recent development of reliable multicast protocols can be found in [13]. These protocols in general focus on a number of issues including group management, flow control and the scalability issues. The protocols can be classified into four types, the ACK based protocols [24, 16] where all receivers send positive acknowledgments for each packet that they receive, the ....

B. N. Levine and J.J. Garcia-Luna-Aceves "A Comparison of Reliable Multicast Protocols." Multimedia Systems, 6:334--348, 1998.

....summary. II. BACKGROUND AND RELATED WORK The first comparative analysis of reliable multicast protocols was done by Pingali et al. 9] They have compared the processing re quirements of the same classes of sender and receiver initiated protocols we will use in our analysis. Levine et al. [10] have extended this work to the class of ring and tree based approaches and showed that tree based approaches are superior in terms of scalability. In [7] a more realistic system model including loss of control packets was analyzed and further protocol classes were introduced. Besides processing ....

B. Levine and J. Garcia-Luna-Aceves, "A comparison of reliable multicast protocols," Multimedia Systems, vol. 6, no. 5, pp. 334-- 348, Sept. 1998.

....Multicast transport protocols use positive or negative acknowledgment schemes to ensure reliable message delivery. A positive acknowledgment returned by a receiver confirms correct message delivery, whereas a negative acknowledgment asks for a message retransmission. It has been shown [1] that tree based multicast protocols scale better than other multicast schemes suggested in the literature. In tree based protocols, the members of a multicast group are organized in a so called ACK tree to overcome the well known acknowledgment implosion problem, i.e. overwhelming of the sender ....

....conclude our work with a brief summary. II. RELATED WORK Reliable multicast protocols were already analyzed in previous work. The first work in this area was presented by Pingali et al. 5] They have compared the processing requirements of sender and receiver initiated protocols. Levine et al. [1] have extended this analysis to the class of ring and tree based approaches and showed that tree based approaches are superior. Bandwidth analysis of generic reliable multicast protocols were done by Kasera et al. 6] Nonnenmacher et al. 7] and Poo et al. 8] In [6] local recovery techniques ....

[Article contains additional citation context not shown here]

B. Levine and J. Garcia-Luna-Aceves, "A comparison of reliable multicast protocols," Multimedia Systems, vol. 6, no. 5, pp. 334-- 348, Sept. 1998.

....4.3.2 IP Multicast To solve the problem of propagation delay of endhost multicast, we can use IP Multicast to send efficiently to many hosts. However, since IP Multicast is built at the IP layer, to this date, no standard reliable transport protocol is available for it. However, research [11, 18, 4] has been done making IPMulticast scalably reliable. For simplicity, we categorize these efforts into two separate categories, Topology Based, and Receiver Based. Topology Based Reliability In this category of reliable IP Multicast, receivers are grouped together in trees, rings or some other ....

....done making IPMulticast scalably reliable. For simplicity, we categorize these efforts into two separate categories, Topology Based, and Receiver Based. Topology Based Reliability In this category of reliable IP Multicast, receivers are grouped together in trees, rings or some other topology [11]. Reliability is ensured by having receivers aggregate their acknowledgments and sending them back to the sender, which retransmits. Local recovery is an enhancement of this, whereby some member of the aggregate group fill the requests for retransmission between themselves [11] The authors of ....

[Article contains additional citation context not shown here]

B. N. Levine and J. J. Garcia-Luna-Aceves. "a comparison of reliable multicast protocols".

....SRM [6] or RMTP [10] Our goal is to provide a layer on top of these services that forces a total order on message delivery. We believe that a layered approach, in which we focus exclusively on ordering, re ects a sensible separation of concerns. Many existing proposals for reliable multicast [6, 10, 11] stack a repair layer on top of an unreliable multicast layer. In the same spirit, we stack an ordering layer on top of reliable multicast so we can focus on ordering independently of repair and retransmission. We distinguish between receiving a message at a node, which typically involves placing ....

B. N. Levine and J.J. Garcia-Luna-Aceves. A comparison of reliable multicast protocols. Multimedia Systems Journal (ACM/Springer), 6(5), August 1998.

.... and loss characteristics of the Mbone [10, 30] These have shown a large amount of heterogeneity in the reception quality for multiple receivers in a single session, posing a challenge to designers of resilient multicast streaming protocols [8, 22] and reliable multicast transport protocols [16]. The loss signature of a receiver is used by a number of protocols to identify subsets of receivers which belong, at least symptomatically, to shared subtrees. This signature has two components: the temporal pattern of packet loss, and the correlation between the position of a receiver in the ....

B. Levine and J. J. Garcia-Luna-Aceves. A Comparison of Reliable Multicast Protocols. ACM Multimedia Systems Journal, August 1998.

....simulation results in Section VI. Finally, we will conclude with a brief summary. II. BACKGROUND AND RELATED WORK The first comparative analysis of reliable multicast protocols was done by Pingali et al. 6] They have compared the processing requirements of flat protocol classes. Levine et al. [7] have extended this work to the class of ring and tree based approaches and showed that treebased approaches are superior in terms of scalability. In [8] a more realistic system model including loss of control packets was analyzed and further protocol classes were introduced. Besides processing ....

B. Levine and J. Garcia-Luna-Aceves, "A comparison of reliable multicast protocols," Multimedia Systems, vol. 6, no. 5, pp. 334-- 348, Sept. 1998.

....these techniques and a series of recommendations for designers of packet based audio conferencing applications. A number of surveys have previously been published in the area of reliable multicast and IP based audio video transport. The work by Obraczka [3] and Levine and Garcia Luna Aceves [4] is limited to the study of fully reliable transport and does not consider real time delivery. The survey by Carle and Biersack [5] discusses real time IP based audio video applications and techniques for error recovery in this environment. However, that work neglects receiver based error ....

....multicast of data objects, they are not generally suitable for streaming media such as audio. This is because they do not bound the transmission delay and, in the presence of packet loss, may take an arbitrary amount of time. A large number of reliable multicast protocols have been defined (see [4] for a survey) which are similarly unsuitable for streaming media and hence are not studied here. For similar reasons, TCP is not appropriate for unicast streaming audio. That is not to say that retransmission based schemes cannot be used for streaming media, in some circumstances. In particular, ....

B. N. Levine and J. J. Garcia-Luna-Aceves, "A comparison of reliable multicast protocols," ACM Multimedia Sys., Aug. 1998.

....suffer from a condition known as feedback implosion, because many receivers attempt to send acknowledgement (ACK) for a single packet. A number of multicast ARQ protocols have been suggested to avoid or reduce the implosion effect, which can be classified to three approaches: send initiated ARQ [21, 11, 12, 13], receiver initiated ARQ [5, 9, 12, 13] and hierarchical ARQ. In the first approach, the message is (re )sent until ACKs from all destinations are received, with the exception of those receivers which are in bad linked condition and will be detached from the multicast link group. The second ....

....implosion, because many receivers attempt to send acknowledgement (ACK) for a single packet. A number of multicast ARQ protocols have been suggested to avoid or reduce the implosion effect, which can be classified to three approaches: send initiated ARQ [21, 11, 12, 13] receiver initiated ARQ [5, 9, 12, 13] and hierarchical ARQ. In the first approach, the message is (re )sent until ACKs from all destinations are received, with the exception of those receivers which are in bad linked condition and will be detached from the multicast link group. The second approach shifts the error control load ....

[Article contains additional citation context not shown here]

B. N. Leviene and J. J. Garcia-Luna-Aceves, A comparison of Reliable Multicast Protocols , Multimedia Systems (ACM/Springer), Vol. 6. No. 5, August 1998.

....of error recovery is distributed (we will call the tree a logical tree, hereafter) Some receivers in the tree are designated to handle the feedback only from their children, and to send retransmissions only to them. Tree based protocols are also known most scalable in terms of throughput [11]. Logical trees should be organized such that the receivers residing at the upper level in a multicast routing tree than ones requesting retransmissions be appointed as parents in a corresponding logical tree. However, as members dynamically join and leave a session or the multicast route changes ....

B. N. Levine and J. J. Garcia-Luna Aceves, "A Comparison of Reliable Multicast Protocols," ACM Multimedia Systems, 1998

....build a hierarchy of subgroups and localize the error recovery. Assumption 4 describes a generic scheme inside each subgroup: proxy based error recovery with multicast retransmissions. There are many other available options very well summarized in [9] analytically compared in a number of studies [23, 26, 12]. Details of feedback and congestion control are ignored here. Our performance metrics capture the total transmissions needed to deliver a packet correctly to all members. If there is no loss, there should be only one transmission per packet. If there are losses, there are extra retransmissions ....

....packet to the entire group, or for the proxy of Figure 2 to reliably deliver a packet to the entire subgroup. 3.1 The E[M] Measure 3.1. 1 Meaning and related work E[M] is an important measure, which first appeared in [1] and ever since has been used in most analytical work on Reliable Multicast [19, 21, 20, 23, 26, 12]. P n l pn pl Figure 2. Inside a subgroup E[M] is defined to be the expected number of times that a packet should be multicast (original transmission retransmissions) by the source, until all group members receive it correctly, at least once. It depends on the shape of the tree and the link ....

B.N. Levine and J.J. Garcia-Luna-Aceves, "A Comparison of Reliable Multicast Protocols", in ACM Multimedia Systems Journal, August 1998

....rst processing requirements analysis of generic reliable multicast protocols was presented by Pingali et al. 8] They compared the class of sender and receiverinitiated protocols. Following analytical papers are often based on the model and analytical methods introduced by [8] Levine et al. [3] have extended the analysis to the class of ring and tree based approaches. In Maih ofer et al. 5] protocols with aggregated acknowledgments are considered. A bandwidth analysis of generic reliable multicast protocols was done by Kasera et al. 2] Nonnenmacher et al. 6] and Poo et al. 9] In ....

....based on aggregated ACKs to be able to cope with node failures. 3. CLASSIFICATIONOFRELIABLEMULTICAST PROTOCOLS In this section we brie y classify the reliable multicast protocols analyzed in this paper. A more detailed and more general description for some of these classes can be found in [8] [3] and [6] 3.1 Sender Initiated Protocols The class of sender initiated protocols is characterized by positive acknowledgments (ACKs) returned by the receivers to the sender. A missing ACK detects either a lost data packet at the corresponding receiver, a lost ACK packet or a crashed receiver, ....

[Article contains additional citation context not shown here]

B. Levine and J. Garcia-Luna-Aceves. A comparison of reliable multicast protocols. ACM Multimedia Systems, 6(5):334-348, Sept. 1998.

....retransmission or repair traffic based upon status reports about the original traffic from receivers. Spatial redundancy refers to providing redundancy within the original transmission, typically in the form of forward error correction (FEC) Excellent surveys of RMT protocols may be found in [20,27,33]. In general, the two key problems which arise in RMT (and proposed solution approaches) are: 1) The implosion of control traffic on the reverse direction from multiple receivers to the sender (M to 1) The proposed approaches to this problem include: ffl Scoped multicasting of reverse control ....

B.N. Levine and J.J. Garcia-Luna-Aceves, "A Comparison of Reliable Multicast Protocols," ACM Multimedia Systems Journal, August 1998.

....will not work correctly; and (b) the delay between any two receivers is small compared to the delay between the sender and the receivers, otherwise the timerbased NAK will not work effectively. In the Internet environments, both of the above conditions may be violated. Besides, as pointed out in [10], NAK based schemes require an infinite buffer at the sender in order to guarantee correct operation while ACK based schemes can guarantee reliable transmission with bounded buffers. We believe that for a dynamic environment such as the Internet, a conservative ACK based scheme is superior (with ....

B. N. Levine J. J. Garcia-Luna-Aceves, "A Comparison of Reliable Multicast Protocols," Multimedia Systems (ACM/Springer), August 1998.

....[DDC97] 2. The PIM Architecture for Wide Area Multicast Routing [DEF 96] 3. Core Based Trees (CBT) An Architecture for Scalable Inter Domain Multicast Routing [BFC93] Week 7: October 20, 1998 Topic: Reliable Multicast Assigned Readings: 1. A Comparison of Reliable Multicast Protocols [LGLA98] 2. Reliable Multicast Transport Protocol (RMTP) PSLB97] 3. A Reliable Multicast Framework for Light Weight Sessions and Application Level Framing [FJL 97] 4 Week 8: October 27, 1998 Topic: Networked Multimedia Assigned Readings: 1. Multimedia Systems: An Overview [Fur94] 2. Network ....

B.N. Levine and J.J. Garcia-Luna-Aceves. A Comparison of Reliable Multicast Protocols. ACM Multimedia Systems, August 1998.

....retransmission or repair traffic based upon status reports about the original traffic from receivers. Spatial redundancy refers to providing redundancy within the original transmission, typically in the form of forward error correction (FEC) Excellent surveys of RMT protocols may be found in [20, 27, 33]. In general, the two key problems which arise in RMT (and proposed solution approaches) are: 1. The implosion of control traffic on the reverse direction from multiple receivers to the sender (M to 1) The proposed approaches to this problem include: ffl Scoped multicasting of reverse control ....

B.N. Levine and J.J. Garcia-Luna-Aceves, "A Comparison of Reliable Multicast Protocols, " ACM Multimedia Systems Journal, August 1998.

....as SRM [5] or RMTP [9] Our goal is to provide a layer on top of these services that forces a total order on message delivery. We believe that a layered approach, in which we focus exclusively on ordering, re ects a sensible separation of concerns. Many existing proposals for reliable multicast [5, 9, 10] stack a repair layer on top of an unreliable multicast layer. In the same spirit, we stack an ordering layer on top of reliable multicast so we can focus on ordering independently of repair and retransmission. As usual, we distinguish between receiving a message at a node, which typically ....

B. N. Levine and J.J. Garcia-Luna-Aceves. A comparison of reliable multicast protocols. Multimedia Systems Journal (ACM/Springer), 6(5), August 1998.

....that try to suppress or reduce source implosion occurrence. We also emphasize the impact of each technique on two important QoS parameters: reliability (full or partial) and response time. Infortunately little work has been done to compare different approach quantitatively. Levine and al. [26] compares protocols each others and gives a good analytical synthesis of the maximum throughput of different approaches. Aggregation: the idea behind this expression is to approach the optimal algorithm for multicast loss detection, that is one request for each loss whatever the number of ....

....Reliable Multicast [19] have been designed to be used by white board application. Ordering is so not supplyed and not mandatory for this type of application reducing so the response time. Local retransmission is possible. SRM uses slotting and damping but one can not says that SRM is scalable (see [26]) STORM The STructured Oriented Resilient Multicast [35] designed for videoconferencing applications, like SRM uses local retransmission but allows each receiver to choice its own compromise between reliability and transfer time. Reliability is not formally full. The service offers no ....

B. N. Levine & J. J. Garcia-Luna-Aceves, "A Comparison of Reliable Multicast Protocols", Multimedia Systems, 1998.

....use, as illustrated in Figure 1. The right branch of this classification, ACK based sender reliable transport, corresponds to conventional reliable transport as used in TCP, for instance. It is also called ARQ (Automatic Repeat reQuest) Simple ARQ does not scale to a large multicast receiver set [21, 22], prompting the use of the left branch of techniques, namely NAK based receiver reliable protocols. Here, each receiver is responsible for detecting losses and sending NAKs to request retransmissions. Scalability is further improved by using distributed recovery, where multiple retransmitters (in ....

B.N. Levine and J.J. Garcia-Luna-Aceves, A Comparison of Reliable Multicast Protocols," Multimedia Systems (ACM/Springer), Vol. 6, No.5, August 1998.

....not updated its document, a client s poll will result in a notmodified reply. With true push, on the other hand, client s do not need to periodically poll the origin server. Origin servers send the latest document update to the subscribed clients as soon as the document update occurs. Multicast [1] is a natural and efficient solution to push document updates to a large number of clients. Multicast shares all common paths between the origin server and the clients, reducing the bandwidth usage and the server s load. Using multicast, clients immediately obtain document updates without ....

B. Levine and J. J. Garcia-Luna-Aceves, "A comparison of reliable multicast protocols," Multimedia Systems, vol. 6, no. 5, 1998.

No context found.

Brian Neil Levine and J.J. Garcia-Luna-Aceves. A Comparison of Reliable Multicast Protocols. Multimedia Systems, 6(5):334-348, August 1998.

No context found.

B.N. Levine and J.J. Garcia-Luna-Aceves. A comparison of reliable multicast protocols. Multimedia Systems Journal (ACM/Springer), 6(5), August 1998.

....nodes have public private key pairs for establishing secure channels to communicate over, and the computation of unicast paths composed of nodes authorized to participate in the active session. The reliability required of APDP is, similar to reliability required of traditional multicast services [9], the assurances that all packets from each source are delivered to each member of the session within a finite amount of time and free of errors, and that packets are safely deleted at the source within a finite time. These assurances are required so that applications using APDP know when ....

....it generates, ideally requiring only one packet on each link used to reach session members. However, the additional requirements of APDP beyond those of traditional multicast pose significant challenges. APDP must be reliable. While work has been done on reliability for traditional multicast [9] no designs have been implemented and widely deployed. APDP must be secure in two senses: security of the data itself, and control of the distribution of the data. Security of the data itself involves the authorization of senders and receivers to access group traffic, and the cryptographic ....

Brian Neil Levine and J.J. Garcia-Luna-Aceves. A comparison of reliable multicast protocols. Multimedia Systems, 6(5), August 1998.

....recovery [42, 65, 27, 26, 18, 64, 30, 38, 24, 31, 57] which necessitates topologically distinguished data. Localized packet loss prevents receivers from receiving retransmissions they do not need. Localized feedback allows reliable multicast protocols to scale with a growing receiver set [28]. Finally, application content and receiver interest presents presents a scenario by which data flows can be distinguished. In a large application, receiver interest can be diverse over a large set of application content. For example, during the broadcast of a football game different camera angels ....

....into a tree structure for sending retransmissions to portions of the receiver set. Organizing the receivers into a tree structure, where each receiver is responsible for a set number of other receivers, has been shown via an analysis model to be the most scalable choice among several methods [44, 28]. Intuitively, reliable multicast protocols that organize trees of receivers for local recovery work well because they distribute the cost of processing Acks, Nacks, and retransmissions, which reduces the load on the source and the network. The question is how to establish such an organized local ....

[Article contains additional citation context not shown here]

B. N. Levine and J.J. Garcia-Luna-Aceves. A comparison of reliable multicast protocols. Multimedia Systems Journal (ACM/Springer), 6(5), August 1998.

No context found.

Brian Neil Levine and J. J. Garcia-Luna-Aceves. A comparison of reliable multicast protocols. Multimedia Systems, 6(5):334-348, 1998.

No context found.

B. N. Levine and J. J. G.-L.-Aceves. A comparison of reliable multicast protocols. Multimedia Systems, 6(5):334--348, 1998.

No context found.

Levine, B. N. and Garcia-Luna-Aceves, J. 1998. A comparison of reliable multicast protocols. Multimedia Systems 6, 5, 334--348.

No context found.

B.N. Levine and J.J. Garcia-Luna-Aceves, A Comparison of Reliable Multicast Protocols, ACM Multimedia Systems, August 1998.

No context found.

B. Levine and J. Garcia-Luna-Aceves. A comparison of reliable multicast protocols. Multimedia Systems Journal, 6(5), Aug. 1998.

No context found.

Brian Neil Levine and J. J. Garcia-Luna-Aceves. A comparison of reliable multicast protocols. ACM Multimedia Systems Journal, 6(5), August 1998. brian.mmsj.ps.gz>.

No context found.

B. Levine and J. Garcia-Luna-Aceves. A comparison of reliable multicast protocols. Multimedia Systems Journal, 6(5), Aug. 1998.

No context found.

Brian N. Levine and J.J. Garcia-Luna-Aceves. A comparison of reliable multicast protocols. Multimedia Systems, 6(5):334--348, 1998.

No context found.

B. Levine and J. Garcia-Luna-Aceves. A comparison of reliable multicast protocols. Multimedia Systems Journal, 6(5), Aug. 1998.

No context found.

B.N. Levine and J.J. Garcia-Luna-Aceves. A comparison of reliable multicast protocols. ACM Multimedia Systems Journal, 6(5):334--348, August 1998.

No context found.

B. N. Levine and J. J. Garcia-Luna Aceves, "A Comparison of Reliable Multicast Protocols," ACM Multimedia Systems, 6, pp. 334-348, 1998

No context found.

B. N. Levine and J. J. Garcia-Luna-Aceves, "A Comparison of Reliable Multicast Protocols," ACM Multimedia Systems, 6, pp. 334-348, 1998

No context found.

B. Levine, J. Garcia-Luna-Aceves, A comparison of reliable multicast protocols, Multimedia Systems 6 (5) (1998) 334--348.

No context found.

B. Levine and J. J. Garcia-Luna-Aceves. A Comparison of Reliable Multicast Protocols. ACM Multimedia Systems Journal, August 1998.

No context found.

B. Levine and J. Garcia-Luna-Aceves, \A comparison of reliable multicast protocols," Multimedia Systems 6, pp. 334-348, Sept. 1998.

No context found.

Brian N. Levine and J. J. Garcia-Luna-Aceves. "A Comparison of Reliable Multicast Protocols," ACM Multimedia Systems Journal, 1998.

First 50 documents  Next 50

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC