J. Kurose. On computing per-session performance bounds in high-speed multi-hop computer networks. In Proceedings of ACM SIGMETRICS, pages 128--139, June 1992.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....of stages of the Erlang random variable is the number of external arrival processes and routing processes contributing to its queue length. Our calculus is built upon the characterization of sources developed in Chang, Thomas and Kiang [9] which in turn is in uenced by Cruz [12, 13] and Kurose [26]. This characterization, called linear upper envelope processes (UEP) basically measures the di erence between an arrival process and a constant rate process. A surprising discovery in this paper, though simple in derivation, is that the di erence is essentially the stationary queue length of a ....

.... Thomas and Kiang [9] was to provide a simple and uni ed proof for various stability results (loose bounds) for open networks of queues, we were surprised that this characterization could also be used to provide tight bounds for intree networks with routing like those in Cruz [12, 13] Kurose [26] and Chang [3, 4] This discovery is mainly based on the following lemma that links the characterization to a stationary queue length distribution. Lemma 2.2 fA(t s; t) 0 s tg st s if and only if max 0 s t [A(t s; t) s] st . Proof. We rst prove the only if part. Since fA(t s; ....

J.F. Kurose, \On computing per-session performance bounds in highspeed multi-hop computer networks," to be presented in SIGMETRICS and PERFORMANCE'92.

....approach to describe arrivals and services in a network. This approach is motivated by the deterministic network calculus [8] which provides an elegant framework for worst case analysis in a network. Several researchers have extended the network calculus to a probabilistic setting, including [5, 17, 20, 22, 24, 26, 28, 27, 29]. An advantage of an envelope approach is that it can provide finite bounds on delay and backlog in a network, as opposed to asymptotic approximations. We present a network calculus in a fully probabilistic setting, where both arrivals and service are expressed in terms of probabilistic bounds. ....

J. Kurose. On computing per-session performance bounds in high-speed multi-hop computer networks. In Proceedings of ACM SIGMETRICS '92, pages 128--139, Newport, RI, June 1992.

.... statistical multiplexing of adversarial traffic, which can consider scheduling algorithms other than a simple multiplexer [7] 12] Related work to this paper are all attempts to consolidate the deterministic network calculus [4] with statistical multiplexing (e.g. 2] 6] 10] 11] 12] [14]) In addition, of particular relevance to this paper are all previous results on statistical multiplexing gain with adversarial regulated traffic, as cited above. We refer to [1] for a detailed discussion of related work. The results derived in this paper only apply to a single node. Since ....

....can re write Eqn. 16) as (18) Remark: The assumption in Eqn. 17) requires further justification, since, in general, the right hand side is larger than the left hand side. On the other hand, several works on statistical QoS have used Eqn. 17) with equality [3] 11] 12] 13] [14], and, in several cases, have supported the assumption with numerical examples. Recall from the definition of the local effective envelope Cp ##; # x implies Pr A Cp #t; t ## #x # . Then, with Lemma 1(a) and assuming that Eqn. 17) holds with equality, we have that a class q ....

[Article contains additional citation context not shown here]

J. Kurose. On computing per-session performance bounds in high-speed multi-hop computer networks. In ACM Sigmetrics'92, pages 128--139, 1992.

....algorithms can be used to bound delay in subnetworks. For example, in [3, 4] algorithms are designed to bound packet delays in an FDDI network. It should be noted that most of the current delay bounding solutions assume a simple network model where link delays between switches are constant [20, 21, 51, 66, 68, 38, 6]. Constant delay links have the desirable property that the traffic pattern at the receiving end of the link is the same as that at the transmitting end of the link. This property is important for these solutions because they use the characterization of the output traffic from a scheduler as the ....

....to establish that holding in the rate controllers will not increase the end to end delay bound. ffl The theorem assumes links with bounded, but possibly variable, delay. Most of the existing solutions proposed to bound end to end delay in a networking environment assume links with constant delay [20, 21, 51, 66, 68, 38, 6]. Constant delay links have the nice property that the traffic pattern at the receiving end of the link is the same as that at the transmitting end of the link. This property is important for existing bounding solutions because central to their analysis is the technique of characterizing output ....

[Article contains additional citation context not shown here]

Jim Kurose. On computing per-session performance bounds in high-speed multi-hop computer networks. In ACM SigMetrics'92, 1992.

....average bandwidth. 2 Related Work The problem of providing various forms of probabilistic and statistical performance guarantees has received considerable research attention. Knightly and Shroff [14] provide a good overview of admission control approaches for link level statistical QoS. Kurose[15] derived probabilistic bounds on delay and buffer occupancy of flows using the concept of stochastic ordering for network nodes that use FIFO scheduling. Unlike FIFO schedulers that inherently cannot differentiate between performance requirements of different real time flows, we are interested in ....

J. Kurose. On computing per-session performance bounds in high-speed multi-hop computer networks. In Proc. of ACM Sigmetrics'92, pages 128--139, 1992.

....could achieve very high network utilization both in a well known network and randomly generated networks. Our methodology presented in this paper can be easily extended to deal with statistical delay guarantees. Much progress has been made in derivation of statistical delay bounds [11] 2] [12], 20] However, all these previous results require information on flow population to obtain the statistical delay bounds. For example, in [11] statistical delay bounds are obtained by using approximated normal distribution, of which the parameters, in turn, depend on the flow population. Our ....

J. Kurose, On computing Per-session Performance Bounds in High-Speed Multi-Hop Computer Networks, Proceedings of ACM Sigmetrics'92, 1992.

....4.1 Related Work on Statistical Delay Guarantees The problem of providing various forms of statistical performance guarantees has received considerable research attention. Knightly and Shroff [25] provide a good overview of admission control approaches for link level statistical QoS. Kurose[27] derived probabilistic bounds on delay and buffer occupancy of flows using the concept of stochastic ordering for network nodes that use FIFO scheduling. Unlike FIFO schedulers that inherently cannot differentiate between performance requirements of different real time flows, we are interested in ....

J. Kurose. On computing per-session performance bounds in high-speed multi-hop computer networks. In Proc. of ACM Sigmetrics'92, pages 128--139, 1992.

....is that if a node o#ers the service curve # and the input is # smooth, then v(#, #) is an upper bound on the backlog at any time. 3 2 A Bounding Method Phase 1: Reduction to Arrival Events. All bounds we present in this paper use the following reduction, which was already found for example in [16, 26, 22, 7]. Events of the interest such as steady state backlog larger than a given value , waiting time larger than a given value , loss for a lossy node larger than a given value , are shown to be subsets of inclusions of the following events; for s t that belong to some countable set: R i ....

....g is some appropriately defined positive valued non decreasing function. The details are given in Section 3. Phase 2: Bounding the Probability of Arrival Events (2.6) A classical approach that was used in the past consisted in posing some a priori bounds for the probability of (2. 6) Kurose [16] assumes that, for each fixed s t, and 1 I, R i (t) R i (s) is stochastically majorized by some known random variable; Yaron and Sidi [26] suppose that the probability of (2.6) is upper bounded by a time invariant exponential and then build calculus under this assumption; this is later ....

[Article contains additional citation context not shown here]

J. Kurose, On computing per-session performance bounds in high-speed multi-hop computer networks, Proc. of ACM Sigmetrics and Performance '92 (Newport, Rhode Island), June 1992.

....scheme can typically support two to three times the number of connections that deterministic service disci plines (GPS, RCS, etc. can support. The problem of providing end to end statistical QoS guarantees in a network has received a great deal of atten tion in recent years. The early works [23], 3] in this area derive probabilistic bounds on the delay of flows in a net work, while [44] discusses a conceptual framework for QoS assurances in a network. A scheme which is able to provide end4o end statistical QoS in a network of Generalized Processor Sharing (GPS) schedulers is developed ....

J. Kurose. On computing per session performance bounds in high speed multi hop computer networks. In Proceedings of ACM Sigmetrics '92, pages 128 139, 1992.

No context found.

J. Kurose. On computing per-session performance bounds in high-speed multi-hop computer networks. In Proceedings of ACM SIGMETRICS, pages 128--139, June 1992.

No context found.

Jim Kurose. On computing per-session performance bounds in high-speed multi-hop computer networks. In ACM SigMetrics'92, 1992.

No context found.

J. Kurose. On computing per-session performance bounds in high-speed multi-hop computer networks. Proc. ACM Sigmetrics and Performance '92, 1992.

No context found.

J. Kurose, "On computing per-session performance bounds in high-speed multi-hop computer networks", Proceeding ACM Sigmetrics and Performance '92, 1992.

No context found.

J. Kurose. On computing per-session performance bounds in high-speed multi-hop computer networks. In Proc. of ACM Sigmetrics'92, pages 128--139, 1992.

No context found.

J. Kurose. On computing per-session performance bounds in high-speed multi-hop computer networks. Performance Evaluation Review, 20(1):128--139, June 1992.

No context found.

J. Kurose. On computing per-session performance bounds in high-speed multi-hop computer networks. In Proc. of ACM Sigmetrics'92, pages 128--139, 1992.

No context found.

J. Kurose. On computing per-session performance bounds in high-speed multi-hop computer networks. In Proceedings of ACM SIGMETRICS '92, pages 128--139, Newport, RI, June 1992.

No context found.

J. Kurose. On computing per-session performance bounds in high-speed multi-hop computer networks. In ACM Sigmetrics'92, pages 128--139, 1992.

No context found.

J. Kurose, "On Computing Per-session Performance Bounds in High-Speed Multi-hop Computer Networks," Proc. of ACM SIGMETRICS 1992.

No context found.

J. Kurose. On computing per-session performance bounds in high-speed multi-hop computer networks. In Proceedings of ACM SIGMETRICS '92, pages 128--139, Newport, RI, June 1992.

No context found.

J.F. Kurose, \On computing per-session performance bounds in high-speed multi-hop computer networks," to be presented in SIGMETRICS and PERFORMANCE'92.

No context found.

J. Kurose, "On Computing Per-session Performance Bounds in High-Speed Multi-hop Computer Networks," SIGMETRICS 92

No context found.

Kurose, J.: On Computing Per-Session Performance Bounds in High-Speed MultiHop Computer Networks. In Proceedings of ACM SIGMETRICS. (1992) 128-139.

No context found.

Jim Kurose "On Computing Per-session Performance Bounds in High-Speed Multihop Computer Networks," appeared in Proc. ACM Sigmentrics and Performance'92, 1992.

No context found.

J.F. Kurose, "On computing per-session performance bounds in high-speed multi-hop computer networks," SIGMETRICS and PERFORMANCE'92.

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