Abstract: A multipoint-to-multipoint multi-cast architecture in an IPATM network is significantly simpler and scales better than existing proposals because it does not require any address resolution architecture and requires substantially fewer resources in terms of virtual circuits (VC), CPU power and memory storage. The architecture includes having both sender and receivers reside on the same delivery tree and only one Virtual Circuit (VC) is used to send data over that tree. The delivery tree is a spanning tree and packets are replicated only on the branches where they are needed. An included algorithm has switches that keep track of the branches of the tree where there are group members. The interleaving of ATM cells is prevented by a VC merging mechanism. A core selection mechanism is provided which optimizes the shape of the tree structure.

Abstract: An ATM transmission system is adapted for the simultaneous transmission (i.e. multicasting) of IP data packets to a plurality of system users, using ATM as a carrier network, and includes an IP/ATM network including clusters of Logical IP Systems (LISs), a multicast address resolution server (MARS) for each cluster, and a multicast router (MCR) for each cluster. The clusters are interconnected through the MCRs which form an inter-cluster backbone for the IP/ATM network. Each cluster includes an integral number of ATM hosts and LISs, the size of a cluster is dependent on physical and administrative constraints, and each LIS, within a cluster, is adapted to support a number of ATM hosts. Multicasting of IP data packets within a cluster utilizes a MARS protocol, and multicasting between clusters utilizes an inter-cluster multicasting protocol (ILMP). All ATM hosts within a cluster, even if supported by different LISs, are adapted to be configured with an address of the same MARS.

Abstract: The present invention provides a very simple and scalable architecture which gives a substantially optimal solution for an IP over ATM network service, by exploiting the QoS of the ATM network, providing shortcut communication when necessary, reducing connection setup delay and smoothing migration from the current deployments, while retaining simplicity. This is achieved by introducing three additional functions to the normal operation of the Classical IP model, namely: flow classification/detection, explicit indication of ATM address and QoS, to the receiver, prior to connection setup and receiver initiated connection setup. The present invention also provides, a multi-cast architecture based on an extension to the Multi-cast Address Resolution Service (MARS) architecture known from IETF.

Abstract: The invention relates to an arrangement for load sharing in computer networks and, more exactly, an arrangement for distribution of traffic, for instance via Internet, from clients (1) to service suppliers who provide services from many servers. The invention makes possible distribution to one of a number of replicated servers. Suitable server is selected for instance on basis of available resources at the interface of the server, or less delay in the transmission. The invention results in better performance and reduced traffic by distribution of the traffic geographically and from a resource point of view. According to the invention, a number of replicated servers (5A-5E) belong to an anycast-group and each anycast-group is connected to a domain name server (2) which has the ability to select one of the replicated servers, so that a router (4) can establish a connection between the selected server and the service-requesting client computer.

Abstract: The invention relates to a device for broadband data service transmission in telecommunication system. The invention aims at implementing bridges in public ATM network, by which public data communication services can be used by private, local networks LAN. The bridges make use of a connectionless data service function by means of broadband data service servers (BDS). The ATM network uses the protocol AAL5. According to the invention the transmission can by that be made without buffering. Preferably respective local network is connected via only one BDS server and the transmission in the BDS network is in streaming mode.

Abstract: The invention relates to an arrangement for load sharing in computer networks and, more exactly, an arrangement for distribution of traffic, for instance via Internet, from clients (1) to service suppliers who provide services from many servers. The invention makes possible distribution to one of a number of replicated servers. Suitable server is selected for instance on basis of available resources at the interface of the server, or less delay in the transmission. The invention results in better performance and reduced traffic by distribution of the traffic geographically and from a resource point of view. According to the invention, a number of replicated servers (5A-5E) belong to an anycast-group and each anycast-group is connected to a domain name server (2) which has the ability to select one of the replicated servers, so that a router (4) can establish a connection between the selected server and the service-requesting client computer.