C.-T. Lea, "What should be the goal for ATM," IEEE Network, pp. 60--66, September 1992.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....would be able to select the building block most suitable for a given connection [Cou 95] Such a modification will introduce more flexibility in the specification of the complete AAL services. 9 CONCLUSIONS The introduction of ATM gave rise to controversial discussions still going on today [Lea 92] Cro 94] KiW 95] Sch 95] A cold analysis shows that ATM is a discontinuity for the LAN environment but this discontinuity also offers possibilities of supporting new services in a more efficient way. It may be a mistake in the long run to try to hide this discontinuity instead of ....

C-T Lea, "What Should Be the Goal for ATM", IEEE Networks, Vol. 6, N 5, September 1992, pp. 60-66

.... of the network (with the result of conflicting the fundamental principle for supporting statistical multiplexing and CBR, which requires that elaborate congestion and rate control schemes be executed on a real time basis inside the network, and not at the edge) BS91] HS91] VS91] DJ92] [Lea92]. One of the most important research issues in ATM is related to the characterization of the arrival process for bursty traffic, which is still an open issue. Actually, there is no agreed definition for the burstiness of such a traffic and, accordingly, different traffic descriptors may be used ....

Lea, C-T.,"What Should Be the Goal for ATM," IEEE Network Magazine, pp. 60 - 66, September 1992.

....40 KISTA Abstract The paper discusses the use of fast circuit switching in future highcapacity networks. We believe that the capacity and the size of the public network will increase to an extent where it is infeasible to rely on bandwidth optimization and dynamic congestion control mechanisms [8]. Dynamic synchronous Transfer Mode (DTM) is a new protocol suite based on synchronous fast circuit switching. It is designed for high speed networks running at several gigabits per second. We believe a large part of the traffic in future high speed integrated networks will result from real time ....

....transfer and synchronize different types of traffic. However, in packet switched networks with unpredictable delay, resynchronization of the traffic at the receiver is a problem. Further, asynchronous networks do not provide means for regenerating the pace of the isochronous stream at the receiver [8]. To create the information society, many users have to get access to the new public high speed networks. However, it should not only be easy to access these services, it must also be easy for new entrepreneurs to provide them. With a high capacity network, the processing capacity is not ....

C-T. Lea, "What Should Be the Goal for ATM", IEEE Network Magazine, Vol. 6, No. 5, Sept. 1992.

.... and resynchronization at the receiver are needed to integrate support for different kinds of traffic [4] One of the main concerns with packet switched networks in general, and ATM in particular, is whether it is possible to realize these mechanisms in a cost effective way [5] 6] 7] 8] 9] [10], 11] DTM, Dynamic synchronous Transfer Mode, is a broadband network architecture developed at the Royal Institute of Technology in Sweden. It is an attempt to combine the advantages of circuit switching and packet switching, in that it is based on fast circuit switching augmented with dynamic ....

C-T. Lea, "What Should Be the Goal for ATM", IEEE Network Magazine, Vol. 6, No. 5, pp. 60-66, Sept. 1992.

....control is receiving a lot of attention, and there are quite a number of related issues which have not been mentioned here. Opinions within the research community range from Statistical multiplexing gains are illusory we should rethink our expectations of the technology or choose another method [12] to Statistical multiplexing gains might not be as great as hoped, but it doesn t Page 7 matter as much as you think to Statistical multiplexing is possible, and here s how we are going to achieve it. 3.3. Other issues There are a number of other open and contentious issues for which space ....

C.T. Lea, What Should Be the Goal for ATM,» IEEE Network, vol. 6, no. 5, 60-66, Sep 1992.

....required in many distributed network computing applications. ATM, proposed by international standards organizations, uses small 53 bytes cells to transmit data in multiples of OC 1 rates (51.84 Mbits sec) Popular data transfer rates for ATM are OC 3 (155.52 Mbits sec) and OC 12 (622.08 Mbits sec) [7, 10]. ATM was initially developed as a standard for wide area broadband networks. The fact that Local ATM networks are appearing in advance of long haul ATM networks, makes ATM an attractive alternative to traditional LANs. ATM networks are characterized by their switch based network architecture. All ....

....we give an overview of ATM technology, and then discuss the configuration of our experimental hardware and software. Finally, we present a description of the four different APIs. 2. 1 Asynchronous Transfer Mode ATM is a method for transporting information by using fixed length cells (53 octets) [7, 10]. It is based on virtual circuit oriented packet (or cell) switching. A cell includes a 5 byte header and a 48 byte information payload. A connection identifier, which consists of virtual circuit identifier (VCI) and virtual path identifier (VPI) is placed in each cell header. The VPI and VCI are ....

C.T. Lea. What Should Be the Goal for ATM. IEEE Network, September 1992.

....must be peak rate controlled and surplus capacity is wasted since statistical multiplexing is precluded. Traffic control for ATM is a highly active research field. Yet there is no clear indication that the suggested methods for statistical multiplexing with quality guarantees are practicable [1][4][7] This article describes an alternative and readily applicable way of reserving capacity for virtual circuits and paths in ATM networks. The reserved capacity is carried without loss in the network with regard to contention (bit errors might still occur) The left over, non reserved ....

....ensure that loss in the system would only be at the packet level in the routers that are interconnected by the ATM network. A similar use is to reserve capacity for signalling channels so that necessary commands may be get through even during periods of congestion. The criticism given by Lea [4] of the pretension to offer statistical multiplexing in ATM with performance guarantees is convincing and forms the justification for our proposal of deterministic service and quality. Also the study of statistical multiplexing done by Bonomi et al. 1] reveals the challenges offered by ....

C--T Lea, "What Should Be the Goal for ATM," IEEE Network, September 1992, pp. 60--66.

No context found.

C.-T. Lea, "What should be the goal for ATM," IEEE Network, pp. 60--66, September 1992.

No context found.

C.-T. Lea, "What should be the goal for ATM," IEEE Network, pp. 60--66, September 1992.

No context found.

C-T Lea, "What Should Be the Goal for ATM", IEEE Network Magazine, Vol. 6, No. 5, September 1992.

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