By Topic

ATM, 1999. ICATM '99. 1999 2nd International Conference on

Date 21-23 June 1999

Filter Results

Displaying Results 1 - 25 of 69
  • 1999 2nd International Conference on ATM. ICATM'99 (Cat. No.99EX284)

    Save to Project icon | Request Permissions | PDF file iconPDF (346 KB)  
    Freely Available from IEEE
  • Bi-directional ABR mechanism (decreasing feedback delays)

    Page(s): 41 - 48
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (644 KB)  

    The ABR mechanism was designed for controlling the traffic flows in ATM networks. The key factor for efficient and stable controlling of traffic control loops is fast transfer of feedback control information from the network back to the traffic source. In ABR mechanism so-called resource management (RM) cells are used for this purpose. The limited number of these control cells is especially noticeable in local area networks with negligible round trip time delays, when lower bit rates (less than 1 Mbit/s) are in question. Bi-directional ABR connections are composed of two independent unidirectional ABR connections each having its own flow of RM cells. Our proposal is to modify existing RM cells in such a way that each RM cell will be able to transfer control information for both directions at the same time. With the use of such modified RM cells and some modifications in network elements, the ABR control loop response time can be substantially reduced for a relatively small price. The number of RM cells in the network and therefore the amount of overhead information remains unchanged View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • IPv6 multicasting over ATM testbed

    Page(s): 125 - 131
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (528 KB)  

    This paper presents the conception and the development of an experimental testbed for the study of Internet protocol version 6 (IPv6) over asynchronous transfer mode (ATM) environments, in the scope of the MEDIA (MARS Extensions Developed for IPv6 over ATM) project. The MEDIA project proposes and explores a number of extensions to the existing IP over ATM multicasting solutions, that make use of the advantages offered by IPv6 and by user network interface version 4.0 (UNIv4) specifications. The proposed architecture accommodates both the integrated services model and the differentiated services model. This study gives special attention to multicast environments View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hand-off and synchronization protocols for supporting multimedia communications in an ATM based wireless network

    Page(s): 59 - 66
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (652 KB)  

    New multimedia service provision, that requires high transfer speeds, and end-to-end network guaranteed delays, is an under-research field in mobile communications. These services are currently supported by ATM networks, that are, in fact the basis of the fixed network in whole mobile communication systems. However, new generations of digital wireless communication systems, based on TDMA, have bandwidth and signalling limitations in supporting these services. An important problem in this scenario is the synchronisation of multimedia flows when a hand-off is performed, and bandwidth management. We propose, for a typical ATM fixed network/TDMA wireless system architecture, some improvements in the synchronisation and bandwidth management process of multimedia flows after a hand-off procedure View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • VTOA/VoIP/ISDN telephony gateway

    Page(s): 230 - 235
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (408 KB)  

    This paper presents the architecture and implementation of a telephony gateway for interworking between ISDN, ATM and IP telephony. In this way, interworking is achieved both within private networks and with the PSTN, address translation being performed according to both the VTOA (ATM interface) and H.323 (IP interface) specifications. The gateway implementation is based on a PC, presenting a cost-effective alternative to the equipment currently available on the market. Moreover, its highly modular software architecture allows new telephony interfaces to be easily added View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A case study of an approach to the deployment of ATM and IP into an international telephony network

    Page(s): 276 - 284
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (684 KB)  

    The paper presents part of the programme that Interoute Telecommunication (UK) Limited have established for the deployment of ATM and IP from the perspective of a network operator who is presented with a wide range of products from different suppliers, all offering comparable solutions. It then considers the issues that were addressed in order to bring the solutions into service at the time required View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Compound VC mechanism for native multicast in ATM networks

    Page(s): 115 - 124
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (900 KB)  

    The growth of new kinds of traffic, and particularly multimedia, leads to changes in the conception of the network. Multimedia group communications pose stringent requirements to the distributed system supporting them. Maybe the most important requirement is that they should allow the communication from a user in a group to the rest of the group in an efficient way. These communications are referred to as multicast communications. The most efficient way to offer them in terms of resource consumption is at the level where either routing or switching are carried out. ATM poses further challenges due to its connection-oriented nature. Some mechanisms have been proposed in the past either for integrating IP multicast with ATM or for providing native ATM multicast but they present some drawbacks, especially in terms of overhead, management, and scalability. This paper presents a new native ATM multicast proposal that solves some of the problems found in other mechanisms. The multicast group is associated to a group of adjacent VCs (compound VC). A unique entry in the switching table is needed to switch the traffic of the entire group by means of a mask. The variable part of the VCI is dynamically changed each time the first cell of a new PDU arrives to a switch View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Flow service order: a computationally inexpensive packet scheduling algorithm to support QoS guarantees for real-time traffic

    Page(s): 285 - 294
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (552 KB)  

    A new strategy for scheduling packets which promises adherence to the quality of service requirements of real-time data (e.g., video) is proposed. We prove that this new algorithm bounds the interpacket delay between two packets. We also arrive at an expression that bounds the average waiting time of a packet. We then show empirical results regarding the performance of our algorithm that we obtained through simulation. A comparison is made between the performance of our algorithm vis-a-vis the previous algorithms View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A flexible signalling protocol for supporting switched AAL type 2 connections in UMTS terrestrial radio access networks

    Page(s): 67 - 71
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (436 KB)  

    This paper presents AAL2 signalling, a new signalling protocol, which is capable of establishing and releasing end-to-end AAL2 connections through a network of AAL2 switches and endpoints. It briefly discusses the applicability of the new protocol in UMTS terrestrial radio access networks and describes a new protocol architecture (called bearer-independent signalling protocol architecture) which makes possible easy deployment of the protocol in theoretically any network environment View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Connecting heterogeneous supercomputers in broadband networks

    Page(s): 324 - 329
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (424 KB)  

    This paper describes some issues to connect supercomputers for metacomputing applications via an ATM gigabit link. Possible solutions based on different communication technologies are presented and the pros and cons for the final implementation are discussed. TCP/IP tuning was investigated to achieve maximal throughput View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Desktop videoconferencing performance based on an ATM metropolitan area network

    Page(s): 316 - 323
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (524 KB)  

    The DIVINE project enables the evaluation of a high quality desktop videoconferencing system on an ATM (asynchronous transfer mode) network. After the presentation of the used methodologies and performance measurement tools, we analyze the quality of service (QoS) of multimedia services implemented on the DIVINE system. Some performance evaluations have been achieved on the OASICE ATM metropolitan area network View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A method for accurate time synchronization through in-service monitoring in ATM networks

    Page(s): 140 - 145
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (492 KB)  

    In this paper, the ATM performance parameters cell transfer delay (CTD) and cell delay variation (CDV), being monitored for in-service measurement or estimation by the operation and maintenance (OAM) system, are proposed to be used to compute the time and frequency off-sets of the local clock relative to a differential-GPS based reference clock, in order to synchronize a local clock View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Linear codes for end to end cell loss recovery in VBR video transmission over ATM networks

    Page(s): 512 - 520
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1148 KB)  

    We present a set of linear codes, namely LEC, to recover from data erasure errors using minimum redundancy that is theoretically possible. The data to be encoded are organized in the form of matrices and the elements are selectively grouped together using XOR operations to generate the code elements. In the paper we describe LEC coding and provide a comparison of the complexity of the coding scheme with that of Reed-Solomon (RS) codes and EVENODD codes. Also, we discuss the application of LEC to the transmission of VBR (variable bit rate) video traffic over ATM networks View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Advanced frame recovery in switched connection inverse multiplexing for ATM

    Page(s): 404 - 412
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (736 KB)  

    Switched connection inverse multiplexing for ATM (SCIMA) has been proposed as a low-overhead scheme for implementing an N×N switch with a port rate of kR using a kN×kN core switch (or k N×N switches) having a port rate of R. By splitting the traffic of a small number of virtual connections into subconnections over multiple low-capacity core switch ports, SCIMA achieves a performance level comparable with that of an equivalent high-capacity port switch. The scheme ensures that each split cell flow is re-assembled and delivered in the original order even in the presence of variable differential delays and highly non-uniform switching path usage. Furthermore, it can seamlessly recover from isolated cell losses within the core switch, as well as detect the loss of a certain number of consecutive cells belonging to the same subconnection. However, it is unable to restore, by itself, the re-assembly cell chain after two or more consecutive cell losses occur in a row on the same subconnection, and has to rely on other recovery means. In this paper, we describe a fault tolerance mechanism called advanced frame recovery, which applies the concept of framing in the asynchronous environment of SCIMA by inserting regular, albeit not necessarily periodic, checkpoints into the split cell flow. When the mechanism is invoked, it discards some of the successfully delivered cells and allows us to restart the chain at a subsequent checkpoint. The advanced frame recovery scheme is used when SCIMA detects consecutive cell losses within the same subconnection; it also serves as an additional measure of integrity checking during regular re-assembly to correct certain vulnerabilities of SCIMA. We present the motivation and implementation details of advanced frame recovery, together with a discussion of the trade-offs of such an open loop (as opposed to feedback driven) sequence control scheme View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hierarchical vector clock: scalable plausible clock for detecting causality in large distributed systems

    Page(s): 156 - 163
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (676 KB)  

    Modern ATM networks possess a multilevel hierarchical structure, where certain sets of physical or logical nodes are grouped together according to physical, geographical, and/or administrative consideration. A distributed application running on top of such network may contain thousands of sites belonging to different logical nodes with the transport channels between them extending through multiple domain boundaries and crossing multiple hierarchical levels. While knowledge of causality between the events in such a system is essential for analyzing the system behavior and ensuring the correct operation through solving various problems related to mutual exclusion, consistency maintenance, fault tolerance and recovery, etc., the accurate tracking of the causality information may be infeasible due to the system's size and lifespan. For example, the communication and storage overhead involved in using the conventional vector clock, which allows causality to be completely characterized, is linear in the number of sites of a distributed system. In this paper we propose a new logical time system, called hierarchical vector clock or HVC, which allows causality to be detected between events in a large distributed system with a high degree of accuracy, while being ideally suited for the hierarchical structure of an underlying network and able to scale gracefully with the increasing number of distributed sites View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A management system providing real distribution of management tasks with time and space independence

    Page(s): 330 - 339
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (984 KB)  

    Actual management systems do not fulfil a number of requirements identified as mandatory for an efficient and effective network management. The simple adoption of solutions like Java's RMI or OMG's CORBA, do not solve all problems and may originate others. This paper describes the architectural and functional model for the proposed management system, that satisfy a number of identified requirements. Special attention is devoted to the information model, proposing a new structure for it. Within the text some simple application examples of ATM networks are given. Finally, a brief analysis of two distinct ATM switches from different vendors is given referring to the possible added value that the proposed system can bring when managing those devices View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Proactive management of MPEG traffic in ATM networks using time sequenced RLS filters

    Page(s): 507 - 511
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (344 KB)  

    The capability of predicting VBR traffic can significantly improve the effectiveness of numerous management tasks such as dynamic bandwidth allocation and congestion control. This work demonstrates the applicability of time-sequenced adaptive filters in linear prediction of statistically multiplexed MPEG (Motion Pictures Experts Group) VBR (variable bit rate) video traffic. Time-sequenced adaptive filters allow for the cyclostationary nature of the input by periodically changing the filter and adaptation parameters. This predictor set up is ideal for predicting multiplexed MPEG traffic which has periodically recurring statistical properties and can be considered as a concatenation of PAR (periodic autoregressive) cyclostationary processes. The viability of the approach is illustrated through computer simulations. A number of half-hour long empirical MPEG-1 traces are multiplexed and, subsequently, the aggregated traffic is predicted. The RLS (recursive least squares) algorithm is used for adaptation. The results indicate that the RLS algorithm clearly outperforms the conventional LMS (least mean square) adaptive algorithm in terms of convergence speed and steady-state mean-square prediction error, and, hence, is a more suitable candidate for such an application View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient buffer management and scheduling in a combined IntServ and DiffServ architecture: a performance study

    Page(s): 236 - 242
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (564 KB)  

    The differentiated services (DiffServ) architecture promises the provision of QoS-enabled networks by following a simple approach that eliminates scalability concerns and which can be implemented and managed in large networks. However, for end-to-end QoS an appropriate signaling scheme, like the resource reservation protocol (RSVP), should be supported. In this combined approach, signaling messages, which are generated by hosts and interpreted by edge routers, are tunneled transparently through the DiffServ core network. The treatment of the signaling messages in the DiffServ cloud is a very important issue, since long delays in their delivery or a high percentage of drops could result in unpredictable and undesirable situations. In this paper, we define a DiffServ traffic class, herein called network control traffic class, that is used by all signaling messages travelling through the DiffServ network. We provide a simulation analysis which evaluates the key properties of the new DiffServ class including priority level, link-sharing bandwidth and link-sharing structure for an hierarchical class-based resource management mechanism referred to as class-based queuing (CBQ), employed by the DiffServ core routers View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance modeling and analysis of IP switching

    Page(s): 466 - 471
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (400 KB)  

    IP switching is a new routing technology proposed to improve the performance of IP routers. In this paper, we study the performance modeling and analysis of IP switching. Our proposed performance models can be used to evaluate the percentage of flows switched and the ratio of the switched path delay to the forwarded path delay in an IP switch. Based on these models, the impacts of different system parameters on the performance are also investigated. Our objective is to develop a design tool for IP switches View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A TINA-based platform for service deployment and usage

    Page(s): 381 - 389
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (808 KB)  

    This paper reports on the experiences with the development of a TINA-based service deployment and usage platform. Within the MESH (Multimedia Services on the Electronic Super Highway) project, such a platform is developed, based on the TINA service architecture and network resource architecture. The platform is built on top of a distributed software component framework that integrates the TINA service components. One of our main experiences is that the TINA architecture clearly separates services from network technologies. This enables a combination various heterogeneous network technologies, like IP and ATM, at the physical infrastructure level View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A feasible scheduling algorithm for per-VC queueing ATM switches

    Page(s): 295 - 304
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (600 KB)  

    This paper introduces a scheduling algorithm for per-VC queueing ATM switches. Our proposed per-VC queueing scheduler (PVQS) achieves a low maximum delay, provides bandwidth guarantee, and fairly allocates excess capacity. The computation in PVQS is carried out on a per-connection basis, not on a per-cell basis which is mandatory in the virtual time-stamp type of approach. This leads to a significant reduction in computational effort and makes PVQS a feasible candidate for practical implementation in per-VC queueing ATM switches View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • ABR rate control for multimedia traffic using microeconomics

    Page(s): 78 - 84
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (576 KB)  

    Multimedia applications are expected to play a more prevalent role in integrated service networks. One method of efficiently transmitting such traffic uses the ABR service class. However, rate control for this class becomes more difficult due to the bursty and somewhat unpredictable behavior of multimedia traffic. This paper presents a microeconomic-based ABR rate control technique that models the network as competitive markets. Prices are affixed to ABR bandwidth based upon supply and demand, and users purchase bandwidth to maximize their individual QoS. This yields a state-less rate control method that provides Pareto-optimal and QoS-fair bandwidth distributions, as well as high utilization. Simulation results using actual MPEG-compressed video traffic show utilization over 95% and better QoS control than max-min or demand-based weighted max-min View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Evaluation of the TCP traffic over the ABR service targeted to support mass storage applications

    Page(s): 85 - 90
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (472 KB)  

    This paper discusses the performance of mass storage applications, that is, backup sessions, over ATM, being serviced by multiple available bit rate (ABR) connections. In particular, the undertaken work has assumed simultaneous ABR connections in the presence of competitive traffic in the network. More precisely, we have (a) evaluated the performance of multiple ABR connections end-to-end, using both the explicit forward congestion indication (EFCI) and explicit rate (ER) mechanisms, (b) studied the adaptation of the ABR sources under the presence of competitive traffic in the network by applying a dynamic fairness scheme and, (c) studied the dynamics and performance of the TCP/IP protocol over the ABR service specified for an ATM network. Moreover, the performance improvement of TCP over ABR, using an “interworking” function between the TCP end-to-end flow control and the ABR rate-based control as well as examine the effect of the “use-it-or-lose-it” function, is considered. Furthermore, the different levels of performance are compared so as to select the optimum values for mandatory ABR service parameters, being the maximum number of cells (Nrm) between two successive resource management (RM) cells and the factors controlling the increase/decrease of the cell transmission rate (RIF: rate increase factor, RDF: rate decrease factor). Finally, the concept of a dynamic UPC mechanism that monitors the ABR traffic contract is identified View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A novel approach to advanced asynchronous transfer mode for high-speed computer communication networks

    Page(s): 220 - 229
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (644 KB)  

    The number of Internet users continues to increase due to the popularity of the WWW (World Wide Web). Intranets and extranets have also become very popular as they enable the efficient use of data within companies and enhance business processing speed. IP (Internet protocol) packets are used to realize most of these computer communication services. IP belongs to the network layer in the OSI reference model, so the transfer performance of IP is influenced by the technology used in the data link layer under the network layer. One communication technology for the data link layer is ATM (asynchronous transfer mode). ATM technology was researched and recommended for B-ISDN (broadband integrated services digital network). We have been tackling an Internet/intranet/extranet backbone system that offers high speed, high throughput, small delay and low cost by IP/MAC (media access control) over ATM. However we faced the problem that ATM does not completely suit IP packet and MAC frame transfer. For example, there is the “dead cell problem” in which the loss of even one of the ATM cells forming the IP packet causes the loss of the entire packet. There is also the “cell tax problem”, in which the overhead of ATM cells is much larger than those of other long distance transfer techniques. Perfect EPD (early packet discard) is impossible because there is no indication bit that means a cell includes the head or tail part of a datagram in the payload. Moreover, intelligent and effective application use is difficult because the cell header has few CLP (cell loss priority) bits. This paper describes the main problems of datagram transfer across existing ATM networks and details a new cell structure that solves these problems. Other issues relating to this remodelling of the existing cell structure are also examined View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analysis of Internet services in IP over ATM networks

    Page(s): 258 - 266
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (696 KB)  

    This paper presents a trace-driven analysis of IP over ATM services from a user-perceived quality of service standpoint. QoS parameters such as the sustained throughput for transactional services and other ATM layer parameters such as the burstiness (MBS) per connection are derived. On the other hand, a macroscopic analysis that comprises percentage of flows and bytes per service, TCP transaction duration and mean bytes transferred in both directions is also presented. The traffic trace is obtained with novel measurement equipment that combines header extraction hardware and a high-end UNIX workstation capable of providing a timestamp accuracy in the order of microseconds. The ATM link under analysis concentrates traffic from a large population of 1500 hosts from the Public University of Navarra campus network, that produced 1700000 TCP connections approximately in the measurement period of one week. The results obtained from such a wealth of data suggest that QoS is primarily determined by transport protocols and not by ATM bandwidth. The sustained throughput of TCP connections never grows beyond 80 Kbit/s with 70% probability in the data transfer phase (i.e., in the ESTABLISHED state) and we observe a strong influence of the connection establishment phase in the user-perceived throughput. On the other hand, the burstiness of individual TCP connections is rather small, namely TCP connections do not produce bursts according to the geometric law given by slow start and commonly assumed in previously published studies View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.