Graphs are commonly used to model the topological structure of internetworks, to study problems ranging from routing to resource reservation. A variety of graphs are found in the literature, including fixed topologies such as rings or stars, "well-known" topologies such as the ARPAnet, and randomly generated topologies. While many researchers rely upon graphs for analytic and simulation studies, there has been little analysis of the implications of using a particular model, or how the graph generation method may a ect the results of such studies. Further, the selection of one generation method over another is often arbitrary, since the differences and similarities between methods are not well understood. This paper considers the problem of generating and selecting graph models that reflect the properties of real internetworks. We review generation methods in common use, and also propose several new methods. We consider a set of metrics that characterize the graphs produced by a method, and we quantify similarities and differences amongst several generation methods with respect to these metrics. We also consider the effect of the graph model in the context of a speciffic problem, namely multicast routing.

New distributed computing applications are driving the development of more specialized protocols, as well as demanding greater control over the communication substrate. Here, a network subsystem that supports modular, finegrained construction of high-level protocols such as atomic multicast and group RPC is described. The approach is based on extending the standard hierarchical model of the x-kernel with composite protocols in which micro-protocol objects are composed within a standard runtime framework. Each micro-protocol realizes a separate semantic property, leading to a highly modular and configurable implementation. In contrast with similar systems, this approach provides finer granularity and more flexible inter-object communication. The design and prototype implementation runing on Mach are described. Performance results are also given for a micro-protocol suite implementing variants of group RPC. 1 Introduction Network protocols that are implemented at high levels of the pro...

this paper. The rest of this paper is organized as follows. An overview of the Clouds project is provided in section 2, followed by an overview of the Clouds paradigm in section 3. The paradigm is the common link between the first implementation of Clouds (Clouds v.1) and the current version (Clouds v.2).

In this paper we propose a distributed protocol for constructing delay-bounded minimum-cost multicast trees in computer networks. The proposed protocol does not require knowledge of the complete network topology. Furthermore, it is unnecessary to know how many nodes are in the networks and which nodes are group members in advance. It is shown, through analysis and simulation on a class of random graphs, that our protocol only uses O(n) messages in the best case, where n is the number of nodes in the networks. Even in the worst case, our protocol uses O(d∗n) messages that has lower message complexity than previous protocols, where d is the average nodal degree.

: : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : xi I Introduction : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 1 A. Effective Communication : : : : : : : : : : : : : : : : : : : : : : : : : 1 B. Group Communication : : : : : : : : : : : : : : : : : : : : : : : : : : 3 C. Multicasting for Multimedia : : : : : : : : : : : : : : : : : : : : : : : 4 II Multicasting Was ... : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 6 A. The Multicast Routing Problem : : : : : : : : : : : : : : : : : : : : : 8 1. Network Assumptions : : : : : : : : : : : : : : : : : : : : : : : : : 9 2. Some Notation : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 10 B. The Shortest Delay Solution : : : : : : : : : : : : : : : : : : : : : : : 10 C. Minimum Cost Multicasting : : : : : : : : : : : : : : : : : : : : : : : 11 D. Low Cost and Delay Trees : : : : : : : : : : : : : : : : : : : : : : : : 13 III Multicasting Is ... : : : : : : : : : : : : : : ...

The prevailing vision for next generation multimedia communication systems is a digital one. However, we anticipate a transitional period in which hybrid networks involving both analog and digital technology will coexist. These analog facilities will include crossbar audio-video switches, CATV distribution systems, and dedicated lines. For some scale of use, these facilities may offer economies for connectivity to conventional analog video equipment. We are interested in connection routing that will be needed in such hybrid networks for services including video conferencing and broadcast media. The routing problem in such topologies resembles but is not identical to that found in telephone systems because of the presence of broadcast connections. We discuss representative topologies, review related work, and describe algorithms and simulation results. In addition we describe a hybrid system that we have implemented in our research lab which involves several A/V switches, CATV channels,...

This paper presents a low-cost algorithm for multicast routing in computer networks. For performance evaluation, it is compared with Link-State multicast routing, which is a low-delay algorithm used by the Internet MOSPF protocol [1]. This new algorithm supports the group concept and the unknown-destination delivery. It uses a minimum average distance method to select the forwarding links to achieve the low-cost goal. Another important feature of this algorithm is that no delivery tree has to be maintained, which eliminates the problem of memory and CPU congestion. Moreover, its computation time complexity is only linear in the group size. Simulation study shows that this algorithm can lower delay by as much as 40 percent for the same offered load, compared with the low-delay algorithm. Keywords: network, routing, low-cost 1 Introduction Routing is one of the most important aspects of computer networks, and unicast routing has been the dominant scheme used in network rou...