Abstract: The present invention is related to high speed packet switching networks and, more particularly, to a process for selecting an optimal path for packets transmission without bandwidth reservation in communication systems supporting both bandwidth-reserved and non-bandwidth-reserved connections. Non-reserved network connections do not have bandwidth set aside either implicitly or explicitly. The lowest delay priority is assigned to non-reserved traffic and the networks drops non-reserved packets when their buffer overflow at intermediate links. Because the data profile over the connections is bursty and non deterministic, reserved traffic does not lead to a full links utilization except on peaks. Therefore, non-reserved traffic can be transmitted when some bandwidth is available on the links.

Abstract: A method based on predefined connection priorities for assigning link bandwidth to a requesting user in a high speed digital network interconnecting network users through a path including network nodes connected through high speed links. According to this method, a predefined reservable link bandwidth is split into so-called nominal bandwidth portions and common bandwidth portions, both assignable to the same connections on a priority basis. Each of the common bandwidth priorities is individually related to a nominal bandwidth priority through a predefined relationship, making the common bandwidth priorities always lower than any nominal priority. In this way the requested link connection bandwidth, whatever be its nominal priority, is made preemptable primarily on all common bandwidth, thus avoiding the disruption of any network connection which is already established.

Abstract: High speed network nodes can establish new connections by preempting existing ones when insufficient bandwidth is available in the network. Numerous preemption priorities are arranged in a limited number of groups and a median priority level is defined within each group. This median, stored in the topology database of each node of the network, permits better bandwidth utilization per group while consuming very little memory space and generating very low traffic overhead.

Abstract: A topology manager within a data communication network including a number of nodes interconnected by bi-directional links, wherein each said node is provided with means for dynamically setting and storing within the node a full topology database including full parent-node-relationship references. The system is is capable of fast path determination and fast spanning tree recovery based on the topology database contents.

Abstract: The routing paths between origin and destination nodes in a packet switching network are selected more efficiently by reducing the total number of links potentially visited by the routing algorithm. The path selection technique involves two phases, the first phase for principal links identification, and the second phase for selection of the best point-to-point path in the network. Principal paths are minimum hop count paths with a transmission delay less than a specified threshold. The algorithm limits the screening of the network links in the second phase to the principal links and excludes the secondary links. The exploration of a much smaller number of links has the advantage to considerably reduce the computation time required for the path selection. The fact the number of principal links is generally small compared with the total number of links potentially explored, allows to limit the additional processing time necessary in case of unsuccessful attempt.