Showing papers on "Overlay network published in 1990"

Topology distribution cost vs. efficient routing in large networks

Abstract: Routing a message in a network is efficient (in terms of weight of the path used to carry the message) when nodes know the full topology of the network. This may not be the case in large networks since a network may be composed of smaller autonomous pieces by design or by requirements on performance, with each piece having less than complete information about other pieces. We present a trade-off between the amount of topology information exchanged among these pieces and the efficiency of routing in the network. The large network that we study is a collection of networks connected by boundary nodes. Each boundary node knows the topology of its network and the connectivity of networks to each other. The question addressed here is how much topology information about each network should be distributed to other networks in order to achieve reasonably efficient routing.

Design and control of networks with dynamic nonhierarchical routing

Abstract: Dynamic routing concepts are described, and the design and control of dynamic routing networks is discussed. The vastly improved performance of the networks is illustrated with examples from operational experience. The evolution of dynamic routing with respect to several future directions is highlighted. These directions are extension to new networks and services, robust design and real-time adaptivity, and extension to interconnecting networks, including the Worldwide Intelligent Network. >

A framework for a national broadband (ATM/B-ISDN) network

Abstract: The authors propose a hybrid packet- and circuit-switched network as a framework for a national broadband (ATM/B-ISDN) (asynchronous transfer mode/broadband-integrated services digital network). Built on the observation that transmission speeds are likely to remain much faster than switching speeds (thus packet switching at peak transmission rates needs to be avoided), the network architecture is a three-tier hierarchy composed of LANs (local area networks), network nodes and DACS (digital access and cross-connect systems). Access to the network is either through direct connection to a DACS or network node, or through the end-user's LAN, which has a gateway to a network node. Each network node is a high-performance ATM packet switch, which accepts input cells at a B-ISDN rate of 150 Mb/s and serves both as LAN-to-LAN interconnect and as a packet concentrator for traffic destined to other network nodes and LANs. To minimize the delay and simplify the implementation of gigabit-per-second packet switching, the network nodes are interconnected by a backbone network of multi-gigabit-per-second fibers and DACS, which provide reconfigurable circuits between network nodes. A congestion control technique using channel sharing that dramatically reduces the required buffer size is proposed. >

Network architectures and switch interface scenarios

Abstract: After describing the network evolution toward the broadband integrated services digital network, intelligent network and telecommunication management network, the authors propose a set of network architectures which aim to bring about an orderly network evolution. One is the nodal system architecture, which prescribes a nodal system composed of physical equipment modules interconnected via a standardized intermodule (M) interface. Switch interfaces should then be considered as a part of the M-interface family. The M-interface structure is also discussed. It is recommended that study of the proposed nodal system architecture, including the related software system architecture, be encouraged. >

An efficient organization for large, network-based multicomputer systems

Abstract: A comprehensive method of organizing polynode systems, that is, multicomputer systems with a potentially large number of elements interconnected by a point-to-point network, is presented. First, an efficient communication method is defined (the performance of which is comparable with that of the iPSC/2-chip) that is completely realized in hardware and eliminates any necessity of using approximation techniques when applying request-response schemes. Distributed decisions based on this communication method provide a versatile mechanism for constructing arbitrary, logical networks with a point-to-point topology. Logical networks serve as basic tools to implement common tasks of a distributed operating system in an efficient and elegant way. A virtual hash tree (VHT) is then chosen as a standard type of a logical network: a VHT can be allotted to an application and can be used by it to administrate object areas in a decentral and dynamic way. Moreover, dedicated logical networks allow applications to formulate distributed algorithms which properly utilize the processing power offered by polynode systems. >

Point to multipoint radio in the British Telecom network

Abstract: The authors address the issues encountered when operating a telecommunications network in a UK rural environment. Some of the difficulties encountered are similar to those experienced in other parts of the world. To provide expedient and cost-effective solutions to the rural communications problems, the use of microwave radio systems has been considered. Trials of such systems have helped in formulating a system definition requirement. From the extensive case studies of rural network problems, it has been concluded that an overlay network of multipoint radio systems will result in an effective way of providing telephony service quickly, to customers which are difficult to serve by conventional means. Tenders for the supply of multipoint systems have been invited and these will be judged against a number of important technical and operational requirements identified from previous field trials.

Communication network with switchable network nodes

Abstract: Known line conductor transmission networks have repeater stations which are provided with distribution frames which must be switched over manually. Recently, the demand is being made to create electronically controlled distribution frames, which are located in so-called network nodes, for the transmission network so that, when a connection films, a standby path can be very rapidly switched. The problem involved is, on the one hand, to input the switching jobs with the suitable information items into the network nodes and to make it possible to check the correct switching-through into the network nodes. … According to the invention, this is achieved by the fact that, in addition to the actual switching jobs, an unambiguous designation of the digital signal connection to be switched is input into the network nodes and that the source network node forwards this designation to the subsequent network nodes so that these can check their switching. On the other hand, there is also the problem of receiving an alarm signal from the network node concerned when disturbances of the digital signal connections occur in the link, without a follow-up alarm being output by subsequent unaffected network nodes. The problem is solved by converting the AIS signal, which is normally forwarded transparently, into a substitute digital signal (EDS) with a standardised frame structure and by signalling the alarm output by means of a particular bit in this substitute digital signal. … …

Atm cross‐connect switch using folded banyan switching network with bypass links

Abstract: A high-speed multiplex transmission system has recently been proposed based on ATM, where the information is divided into fixed-length blocks called cells, and transmitted on asynchronous multiplexing basis. As the switch to be used in the transit node in such a transmission system, various kinds of switching networks have been proposed, composed of two-input × two-output switch elements with internal buffers. Among those, the multistage buffered Banyan structure, which is a cascade connection of two Banyan networks as the distribution and routing networks, is of a distributed structure, being suited to LSI implementation. The network is a promising candidate since it realizes the self-routing and is stable against a variety of traffic. However, this switching network has a problem in that the delay is increased with the scale of the network, and the in-service expansion of the switching network is not easy. This paper proposes a new network topology of the Banyan network with bypass links, together with the self-routing method, and describes its performance. The network is composed of the distribution and routing networks with bypass links between individual unit switches. By transferring cells from the distribution network to the routing network through the bypass links at appropriate stages, the delay is reduced. The in-service expansion of the system is made easy.

A reliable and fault-tolerant interconnection network

Abstract: An interconnection network with multistage redundant paths is introduced for using in high-performance multiprocessor systems. The routing algorithm of the proposed network is simple and dynamically reroutable. The analysis of the fault-tolerance and performance of the network are given. It is shown that the probability of acceptance and the performance-to-cost ratio of the network are better than those of F and Gamma Networks. Another advantages of the proposed network is the smaller amount of interstage links compared with F network.

A trace-driven analysis of the 'wrap-around' network

Abstract: Performance of the wraparound network through trace-driven simulation is examined. This network has a processor attached to each node, but the links in the network are unidirectional, and the two ends of the network are joined together. Traces of three representative parallel engineering/scientific programs are used as input to the simulator, and the performance of this network is compared to that of an omega network under the same inputs. The wraparound network and the omega network are found to perform similarly, while the size and cost of the wraparound network are smaller than those of the omega. >

Performance benefits of state-dependent routing of telephone traffic

Abstract: The performance improvement that can be realized by changing from the current hierarchical routing scheme to a nonhierarchical state-dependent routing scheme is shown by means of call-by-call simulations in a 52 end-office metropolitan network model. The results show significantly lower blocking especially under load forecast errors and overloads, and better performance under facility failures owing to automatic network management, thus enhancing network survivability. It is noted that these benefits should become more valuable as the telephone operating companies install high-capacity fiber links, which enlarge the potential impact of failures in network elements. >