An implementation of a synchronization mechanism in transport protocol to support multimedia applications over a packet or cell switched network is proposed. In designing such a mechanism for practical use, ease of implementation and capability of handling random delay of packets are two key issues for success. Since the random delay of packet or cell switched networks makes synchronization among media more complicated after the transmission across the network, a model which considers the random transmission delay is hence required to specify the temporal relationship among media. Therefore, a real-time synchronization model is presented to satisfy this requirement in the paper. Based on the proposed synchronization model, a transport protocol, namely the multimedia synchronization transport protocol (MSTP), is designed and implemented. We have implemented a prototype system using the MSTP protocol and built a simulation system for the wide area network (WAN) environment in order to evaluate the performance of the MSTP protocol.

In this paper, an architectural design and implementation of a multimedia conference system over FDDI networks is presented. In this development process, various critical design issues are considered and approaches are proposed to optimize the architectural design to yield acceptable performance. The issues include 1) multicasting capability, 2) design of high speed transport protocol, and 3) delay and jitters performance of FDDI synchronous service.

In considering a transport layer protocol for multimedia applications in packet networks, real-time and synchronization characteristics of multimedia applications have to be considered. Synchronization means that the intermedium temporal relationship for an application has to be satisfied, after the transmission across the network. Since the random delay of packet networks makes synchronization among media more complicated, a model is required to specify the temporal relationship among media across the network which can be easily implemented in a transport protocol. In the paper, a real-time synchronization model (RTSM), is presented for synchronization, and a new protocol, namely MSTP (multimedia synchronization transport protocol), is proposed based on RTSM.>

A Banyan switch with bypass queue can overcome the problem of head of line blocking. This paper presents the throughput analysis for such a switch and the optimal window size for the bypass queue is also obtained. Moreover, to reduce the effect of the internal blocking and to increase the throughput, a parallel Banyan switch with bypass queue is also discussed and analyzed.>

An implementation of a multimedia conference system with shared white board developed on workstations under UNIX environment is presented. During the implementation, some design issues are encountered, such as how to choose transport protocols, how to resolve problems of delay jitter, how to setup and manage the connections, how to resolve the lip synchronization problems, how to assign priority to packets, and how to choose encoding schemes for audio and video. These design issues are discussed.

Article Real-time software-based video coder for multimedia communication systems Share on Authors: Ho Chao Huang View Profile , Jau-Hsiung Huang View Profile , Ja-Ling Wu View Profile Authors Info & Claims MULTIMEDIA '93: Proceedings of the first ACM international conference on MultimediaSeptember 1993 Pages 65–73https://doi.org/10.1145/166266.166273Online:01 September 1993Publication History 7citation1,721DownloadsMetricsTotal Citations7Total Downloads1,721Last 12 Months2Last 6 weeks1 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

The performance of job scheduling is studied in a large parallel processing system where a job is modeled as a concatenation of two stages which must be processed in sequence. P/sub i/ is the number of processors required by stage P as the total number of processors in the system. A large parallel computing system is considered where Max(P/sub 1/, P/sub 2/)>or=P>>1 and Max(P/sub 1/, P/sub 2/)>>Min(P/sub 1/, P/sub 2/). For such systems, exact expressions for the mean system delay are obtained for various job models and disciplines. The results show that the priority should be given to jobs working on the stage which requires fewer processors. The large parallel system (i.e. P>>1) condition is then relaxed to obtain the mean system time for two job models when the priority is given to the second stage. Moreover, a scale-up rule is introduced to obtain the approximated delay performance when the system provides more processors than the maximum number of processors required by both stages (i.e. P>Max(P/sub 1/, P/sub 2/)). An approximation model is given for jobs with more than two stages.>

A performance measurement of the processing overhead of TCP/IP on personal computers interconnected by Ethernet is given. In this measurement of the processing overhead comes from TCP and the Ethernet device driver. For TCP, a large portion of the overhead comes from the checksum computation. Almost all overhead of the lower layer comes from moving data from the main memory to the Ethernet card. Hence, if the bus speed can be increased and the TCP checksum can be performed by hardware, the processing overhead generated from TCP/IP and lower layers can be greatly reduced. The results presented shed light on designing communication protocols on personal computers.>

The authors model a job in a parallel processing system as a sequence of stages, each of which requires a certain integral number of processors for a certain interval of time. They derive the speedup of the system for two cases: systems with no arrivals, and systems with arrivals. In the case with no arrivals, their speedup result is a generalization of Amdahl's law (G.M. Amdahl, 1967). They extend the notion of power as previously applied to general queuing and computer-communication systems to their case of parallel processing systems. They find the optimal job input and the optimal number of processors to use so that power is maximized. Many of the results for the case of arrivals are the same as for the case of no arrivals. It is found that the average number of jobs in the system with arrivals equals unity when power is maximized. They also model a job in such a way that the number of processors required continuously varies over time. The same performance indices and parameters studied in the discrete model are evaluated for this continuous model.>

The authors introduce a tree protocol with collision detection, which not only significantly improves the throughput and delay performance of the original protocol without collision detection but also obtains a higher throughput and lower delay than Ethernet. In addition, when the channel propagation delay is small, the authors use a modified M/D/1 model to approximate the mean and distribution of the delay performance, and show that such an approximation is in close agreement with the simulation results. Since M/D/1 achieves the lowest delay for all protocols, the delay performance of this protocol is very close to the best delay performance for all random access protocols when the channel propagation delay is small. Two modified protocols are given to resolve the synchronization problems encountered when implementing a multiaccess algorithm.>