This paper addresses end-to-end connectivity planning and call admission control for a high capacity multi-beam satellite network with on-board cross-connectivity. On board satellite switching is a technology designed to offer multimedia services, especially in demographically dispersed areas. Nevertheless, full on-board switching techniques are far from maturity. Their implementations have been proven expensive and difficult. There are also high risks involved in launching satellites for the stationary orbit surrounding the earth. As a substitute, a satellite network with on-board cross-connect is devised in this paper. Connectivity planning and call admission control mechanisms associated with such a network are also presented. Simulation studies are conducted to show the effectiveness of the proposed mechanisms.

There are many system proposals for satellite-based multimedia communications that promise high capacity and ease of access. Many of these proposals require advanced switching technology and signal processing on-board satellites that will directly impact their cost, performance, availability, and time-to-market. Given the amount of commercial and technical risk involved in such complex systems, satellite operators have been looking for solutions that are simpler, yet flexible. One solution is based on a geosynchronous (GEO) satellite system equipped with simple on-board processing and switching. The satellite network is ATM-based and carries heterogeneous traffic. An important feature of this system is allowing for a maximum number of simultaneous users, hence, requiring effective connection admission control (CAC) and bandwidth on demand (BOD) algorithms. Nortel Networks has already developed an innovative CAC and BOD algorithm for the system. We present the BOD performance evaluations of the integrated algorithm. By detailed simulations, we show that the BOD scheme is able to efficiently utilize all available bandwidth and to gain high throughput. We also find that the end-to-end delays for voice traffic in the system falls well within the ITU's QoS specification for GEO-based satellite systems. The application buffer sizes observed in the simulations can serve as a guideline for ground station and satellite on-board memory design.

We investigate the impact of uplink multiple access schemes on traffic reshaping for a meshed broadband VSAT network over geostationary (GEO) satellite. The system includes a bent-pipe satellite with a number of broadband VSATs carrying multimedia traffic. An integrated CAC and BOD algorithm is used for the uplink M-TDMA access. An OPNET(TM) simulator is developed to investigate the affects of the CAC/BOD algorithm on the different applications in the satellite networks. Source application traffic is modeled using one of the following ATM transfer capabilities; CBR, rt-VBR, nrt-VBR, ABR, and UBR. We perform detailed traffic studies to compare the source traffic with the traffic out of the uplink multiple access, We show by simulation and analysis that all traffic contracts for the CBR, rt-VBR, and nrt-VBR source traffic are violated after uplink access. The results provide guidelines on the design of a corrective traffic reshaping function that counter-acts the traffic reshaping caused by the CAC/BOD uplink multiple access of the satellite networks.

Small switching elements are the key components of multistage interconnection networks (MINs) used in multiprocessors and in high speed switching fabrics. Clock design for synchronous MINs is an important issue. The existing models assume that the clock period consists of two parts. The control messages are transferred between switching stages during the first part, and the actual data transfer takes place during the second part. We propose a new control design for single queue MINs that reduces the duration of the clock period by making use of output buffers and acknowledgments. The reduction in the clock period comes from the addition of two-unit output buffers, introducing a sophisticated hardware control mechanism, and sacrificing the FIFO feature. We develop an analytical model to compare its performance with the existing designs reported in the literature. We validate our model with extensive simulation studies.

Two self-stabilizing topology maintenance protocols for high-speed networks are presented. The protocols tolerate any number and kind of initial faults. The new protocols improve on previous protocols by their stabilization time (the amount of time following the last topology change required to notify every processor of the correct topology), by their utilization of limited switch bandwidth, and by their avoiding the use of unbounded sequence numbers. The first protocol stabilizes in O(log d) time in the worst case, where d is the diameter of the network. This protocol imposes a high bandwidth requirement on individual network nodes. The second, which is implemented by two software layers, reduces the processing load on individual nodes and stabilizes within O(d) time in the worst case and O(1) time when changes are infrequent.

Fiber optic communications offer a combination of high bandwidth, low error probability, and gigabit transmission capacity. To take advantage of the data transmission rates offered by a fiber optic transmission medium, it is essential to have network processing components that can cope with these rates. One approach to removing the protocol processing bottleneck present in network layers is the PSi architecture. PSi consists of header, connection, and output processors. In this paper, we design a RISC architecture for the PSi header processor. The architecture consists of a two stage pipeline microprogrammed processor with a clock frequency of 50 Megahertz and a throughput of one million packets per second. The specific protocol for which this processor was microprogrammed is the Logical Link Control IEEE 802.2 protocol for LANs.>

Considers the problem of fault-tolerant leader election in asynchronous complete (fully-connected) distributed networks. The processors are reliable, but some of the communication channels may fail intermittently before or during the execution of the algorithm. Channel failures are undetectable due to the asynchronous nature of the network. Let n be the number of processors in the network and f be the maximum number of faulty channels incident on each processor, where f/spl les/ 1/2 [n-1]. Our algorithm uses at most O(n/sup 2/+nf/sup 2/) messages to elect a unique leader of the network. Each message consists of at most O(log|T|) bits, where |T| is the cardinality of the set of processor identifiers. All previous algorithms either tolerated only benign failures such as fail-stop failures, assumed that the network is synchronous, tolerated only a small number of failures, or assumed that the faults are detectable. Our algorithm is the first election algorithm that is designed specifically for asynchronous intermittently faulty complete networks in which up to 1/4 n[n-1] channels may be faulty, where each processor is adjacent to no more than 1/2 [n-1] faulty channels, and where the faults are undetectable.>

We improve on I. Cidon, I. Gopal and S. Kutten's leader election algorithm (Proc. 7th ACM Symp. Principles Distrib. Computing, Toronto, Ont., Canada. Aug. 1988) by presenting an algorithm that uses only O(/spl radic/n log D + f) time units to run on synchronous networks of degree f and diameter D, where f/spl ges/3. When f is 2, the algorithm uses only O(log D) time units.>

A fast time-driven algorithm for topology maintenance in high-speed networks is presented. The algorithm uses only four time units for each broadcast by each computer. The best previous algorithm required O(log m) time units for each broadcast by each computer, where m is the number of currently operational computers in the network. In addition to its speed, the presented algorithm makes several significant contributions. I. Cidon et al. (1988) have shown that Omega (log m) time units are necessary for time-driven topology maintenance algorithms of high-speed networks that do not allow a packet to traverse the same edge in both directions. The proposed algorithm shows that this lower bound does not hold for networks that do allow a packet to traverse the same edge in both directions. The O(log m) algorithm assumed that it takes each computer at most one time unit to simultaneously broadcast messages to all neighbors of the computer. In contrast, a node in the proposed algorithm can send at most, one message per time unit. As in the O(log m) algorithm, the algorithm requires O(D) broadcasts per node before all nodes know the correct topology of the network, where D is the diameter of the currently operational portion of the network.>

The implementation of a combined flow control and optimal routing algorithm in packet switched networks is discussed. An analysis is made of the influence of various objective functions on maximum link utilization, average packet delay and fairness. How the parameters in the proposed objective function affect network performance measures like the flow in the entire network, amount of rejected traffic, maximum link utilization, average packet delay, and unfairness among users is studied. These measures are evaluated for various networks and traffic configurations, and, on the basis of these studies and results, suggestions are made for obtaining the best network performance and utilization.>

A cluster management scheme for dynamic networks, the purpose of which is to maintain the cluster structure of the hierarchical network as a balanced-tree topology is presented. The theoretical time complexity bounds of the cluster management scheme for node birth and death are derived. The effects of the cluster management on gate-connected fixed-node networks under heavy intercluster traffic situations are discussed. In order to show that the scheme can handle realistic communication networks, routing tables and OD pair shortest path routing are used. The settle-down time, throughput, and end-to-end link delays of a network that uses cluster management and a network of the same topology that only uses flooding are compared.>

Electron in asynchronous complete networks is considered for the case in which the links may fail intermittently and undetectably. Undetectable link failure is consistent with the standard model of distributed algorithms in which link delays can be arbitrary but finite. An algorithm is given that correctly solves the problem when the links fail before or during the execution of the algorithm. If n is the number of nodes in the network, f the maximum number of fault links, and r a design parameter, the algorithm uses no more than O(nrf+(nr/(r-1) log(n/(r-1)f))) messages, runs in time O(n/(r-1)) f, and uses at most O(log mod T mod ) bits per message, where mod T mod is the cardinality of the set of node identifiers.>