An efficient bandwidth management and access arbitration scheme for an I/O bus in a multimedia workstation is presented. It assumes that a multimedia workstation consists of a number of processing modules which are interconnected by a packet bus. The scheme is efficient in the sense that it allows the bus to support both continuous media transfers and regular random transactions in such a way that continuous streams can meet their real-time constraints independently of random traffic, and random traffic is not delayed significantly by continuous traffic except when traffic load is very high. Implementation guidelines are provided to show that the scheme is practical. Finally, the performance of this scheme is compared with alternative solutions through simulation.

A multimedia ATM network is shared by media streams with different performance requirements. For media streams such as file transfers, the preservation of bursts and the provision of guarantees for loss probability at the burst level is of primary importance, while, for media streams such as voice, loss guarantees at the cell level are sufficient. Continuous media have stringent delay jitter requirements. Finally, some applications require loss-free transmission. In this paper the first complete traffic management scheme for multimedia ATM networks is introduced supporting a wide variety of quality of service requirements. The operation of the traffic management scheme is completely specified, and real-time admission control algorithms are provided.>

Cell loss is an inherent problem of ATM networks. The magnitude of the service degradation caused by cell loss depends on the application and loss distribution. This paper introduces a new performance criterion, called effective loss, which can quantitatively measure this degradation. Effective loss is particularly suitable for block-oriented transmissions, such as file transfer applications, but can also be applied to a broad range of other applications. In this paper the effective loss measure is applied to the study of the effectiveness of bandwidth reservation mechanisms in an ATM multiplexer. Numerical results demonstrate circumstances under which bandwidth reservation improves performance as well as circumstances in which it degrades performance.>

A traffic control mechanism capable of monitoring and controlling a rich family of incoming traffic behavior is introduced. The traffic control mechanism is capable of supporting a number of different cell time scale control and resource allocation schemes. For each of a variety of incoming cell sequence time behaviors and a given control and resource allocation scheme, the grade of service that can be provided by the traffic control mechanism is determined. Some possible roles for the traffic control mechanism in a traffic control infrastructure are presented along with the detailed performance analysis. Some new results on the stochastic behavior of a bursty source are included.>

The authors discuss the unfairness issue arising in a 802.6 distributed queue dual bus (DQDB) network at heavy loads. Based on the 802.6 protocol, the end-nodes along a bus experience longer delays than the other nodes. The origin and remedy for this heavy load unfairness problem are discussed. An access control scheme is proposed as a solution. A comparison of the proposed scheme with the 802.6 protocol is presented. The simulation results and performance characteristics are discussed under several types of loads. With symmetric load conditions under the proposed scheme, all active nodes along a bus experience almost the same access delay and packet loss characteristics. The performance under several other load conditions was also found to be satisfactory.>

Load-balancing algorithms for Jacksonian networks are derived. The state of the network is represented by the total number of packets for which the source has not yet received an acknowledgement. The networks studied are subject to state-independent routing and state-dependent and state-independent flow control. The objective is to maximize the throughput of the network so that the end-to-end expected packet time delay does not exceed an upper bound. The optimal flow control is shown to be of a window type, while the routing policy balances the traffic inside the network. Several load-balancing algorithms are evaluated.>