World Wide Web (WWW) pages are the vehicle of complex information generated from different sources and with different objectives. This paper proposes to complement the ordinary, pull based, Web browsing architecture by exploiting readily available technologies which address the requirements of a large part of the information. In our solution, push technology and IP multicasting enable the source originated delivery of content to multiple users. Moreover, the real time protocol offers a means to address the delivery of time sensitive content. Ordinary WWW browsers have been used to prove the effectiveness of the proposal in a prototype implementation. Advertising banner delivery, news multicasting and fair electronic auctions are among the target applications of our solution.

Extended generalized shuffle (EGS) networks are a wide class of interconnection networks introduced by Richards (1993). In this work, we study the blocking performance of EGS networks under point-to-multipoint traffic. Two new routing algorithms for multicast connections in EGS networks are defined, and a theorem proving that these algorithms construct minimum-cost connection trees is enclosed. Simulation results show that the blocking performance of EGS networks under multicast traffic is much better than that of three-stage Clos networks of equal complexity.

Great interest in recent years has been devoted to mobile communications, as well as to Internet and IP based networks. The most promising protocol proposals for the handling of host mobility in IP networks are Mobile IP (MIP) and Route Optimization Mobile IP (ROMIP). The two schemes have been contrasted in the case of wireless mobile hosts linked by means of a wired backbone. The simulation results show that the performance in terms of packet delay and loss as well as the overhead of control traffic largely depend on the offered traffic pattern.

This paper gives a snapshot of the convergence of the telecommunications and computer industries to a common vision of networking models for an integrated services information infrastructure meeting the stringent requirements of multimedia applications. First we summarize the requirements and elements of such an infrastructure and introduce a networking model that is framed into four layers: interconnection (bearer), internetworking, interoperability (middleware), and application. Then, we offer a review of the classical telecommunications networking model, the current status of asynchronous transfer mode (ATM) multimedia networking features, and the ongoing activities for fostering evolution of telecommunications networks to enhance control, management, and service delivery. An overview of the current Internet network architecture follows, presenting the recent achievements and the evolving networking protocols to cope with real-time multimedia applications. As described in this paper, the schemes for integrating Internet protocols (IPs) and ATM resource reservation protocols, which address an efficient resource utilization and quality of service guarantee in broadband networks, fall into the first two lower architectural layers, which are the foundation of network computing and communications services. In particular, we present a summary description of the comparative features of both IP and ATM protocol approaches, and we report on current proposals for provisioning IP on ATM networks. Last, we discuss trends in middleware services, including the emerging technology of transportable computation and intelligent agents. Interoperability of heterogeneous networked systems is based on an agreed distributed application encoding and computation environment, thus pushing the key capability of the layered networking architecture up into the middleware layer.

We study a scheme that allows a smooth increase of the capacity of a cellular system for circuit-switching by applying cell-partitioning and dynamic channel allocation techniques. A bound is computed for this reuse partitioning scheme that gives the maximum theoretical gain accomplished in the system bandwidth. The performance of the proposed scheme, in terms of blocking probability, is evaluated both when the position of the mobiles remains unchanged and when mobility is taken into account. The numerical results show that the capacity of the proposed scheme is higher than that of a fixed allocation scheme.

This paper presents a new architecture for the third-generation mobile systems, capture-division packetized access (CDPA), that overcomes most of the limitations of present cellular systems. It addresses the three main issues of radio access, namely the channel reuse, the multiple access, and the handover problems, in complete adherence to packet-switching principles. The CDPA channel reuse mechanism is a completely new alternative with respect to time-division, frequency-division, or code-division multiple-access (TDMA, FDMA, and CDMA, respectively), which achieve communication parallelism by subdividing the bandwidth a priori among cells. In CDPA, a single frequency channel is used and parallel transmissions are achieved through the "capture" capability of receivers. The hybrid reservation-polling multiple access mechanism used in CDPA is able to integrate any kind of traffic and guarantees almost immediate retransmission of packets that are not captured, thus assuring their correct reception. Finally, the packet-switching approach allows connectionless communications with any base station (BS), and eliminates the need for extra radio traffic in managing handovers. This turns out to be very effective in local area systems where the required high bandwidth is obtained by using a pico-cell structure. We present the CDPA architecture, discuss some implementation issues, and evaluate its performance under a variety of system parameters and operating conditions, using analytical and simulation methods.

The paper studies three-stage switching networks capable of routing point-to-multipoint connections. Strict-sense non-blocking operation is addressed and, in particular, the necessary and sufficient condition for a three-stage switching network to be strictly non-blocking when it is offered point-to-multipoint traffic is derived. This condition is given as a function both of the minimum and the maximum number of network outlets addressed by each connection. In this respect, the paper extends the well known Clos' result, giving the necessary and sufficient condition for a three-stage switching network to be strictly non-blocking when it is offered point-to-point traffic. The complexity of a three-stage network is lower than that of a crossbar of equal size only for small values of the maximum admissible fanout of the incoming connections.>

The bidirectional Manhattan street network (BMSN) and the ShuffleNet (SN), four-connected topologies implementing the logical layout of so-called multichannel metropolitan area networks (MANs), are considered. An open issue in multichannel MANs, namely, broadcast service, is addressed. Two different strategies are proposed to deliver broadcast traffic in BMSN and SN, and they are compared on the basis of throughput and delivery delay results, as obtained by developing an analytic model. The availability of an analytic model allows the effectiveness of the proposed algorithms in large size networks to be investigated.>

The authors evaluate the performance of two different network architectures, implementing multichannel metropolitan area networks (M-MANs). Deflection routing, no internal storage, and a high connectivity degree are the main characteristics of regular networks built by interconnecting small-size multichannel nodes. Analytical models have been developed for network architectures with a connectivity degree equal to four: the bidirectional Manhattan street network (BMSN) and the shuffle net (SN). The authors evaluate the performance under uniform traffic distribution and also under the realistic assumption that the user's attachments to network nodes are equipped with input and output buffers. The performances under investigation are throughput, average delay, and packet loss. The availability of an analytical model makes it possible to investigate the performance of networks with a large number of nodes. The strong and weak points of the two M-MAN architectures are pointed out in the discussion of the results.>

The optimality of a dynamic adaptive bandwidth allocation mechanism on the inter-FDDI virtual circuits is analyzed. The proposed algorithm is based on the monitoring of InterWorking Unit buffer status and the request of quanta of bandwidth as the buffer content exceeds given thresholds. By using the analytical model proposed, the analysis of N-level bandwidth quantization algorithm performance can be carried out. The results, validated by simulation, allow comparison between three-level and two-level algorithms. The three-level algorithm shows a better response to statistical fluctuations of input traffic, while offering a better grade of service.>

The problem of a transparent interconnection of remote fiber distributed data interface (FDDI) networks, through broadband ISDN (B-ISDN), forming an internet which could be defined as an extended FDDI is investigated. A hybrid interworking method is proposed that keeps connectionless transfer mode on FDDI and a connection-oriented mode on B-ISDN. The major focus of this work is on a bandwidth allocation algorithm that allows the remote gateways to size the transmission bandwidth on the B-ISDN links according to the traffic needs. The proposed algorithm prevents congestion on receiving gateways and B-ISDN.>