Abstract: A communications network comprises a lower transport layer and an upper overlay incorporating a plurality of routers. Adjacencies are defined between respective pairs of routers. Path protection is provided by defining a software model of the overlay of the network and defining in the model a hierarchy of protection levels for the main path. Each protection level is characterised by a respective set of one or more broken adjacencies in the model, the adjacencies to be broken being determined from a knowledge of the underlying topology. A protection level is selected and a protection path avoiding the broken adjacencies associated with that protection level is calculated. If this calculated path is not available in the real network, a lower protection level in the hierarchy is selected and the protection path calculation repeated. The process continues until a suitable protection path is identified.

Abstract: Congestion control in a communications network, e.g. an Internet Protocol (IP) network, is effected by controlling the egress rate of traffic from the output buffer of the system routers or switches. The traffic egressing from an output buffer is sampled at sequential intervals to determine a bit rate at each interval. An autocorrelation function is calculated from these samples and is used to provide an estimated statistical measure or parameter indicative of congestion and related to a long range dependence of the traffic. A calculation is then made as to whether an increase or a decrease in the buffer output rate would result in a decrease in the congestion parameter, and the buffer output rate is adjusted accordingly.

Abstract: Congestion control in a communications network, e.g. an Internet Protocol (IP) network, is effected by controlling the egress rate of traffic from the output buffer of the system routers or switches. The traffic egressing from an output buffer is sampled at sequential intervals to determine a bit rate at each interval. An autocorrelation function is calculated from these samples and is used to provide an estimated statistical measure or parameter indicative of congestion and related to a long range dependence of the traffic. A calculation is then made as to whether an increase or a decrease in the buffer output rate would result in a decrease in the congestion parameter, and the buffer output rate is adjusted accordingly.

Abstract: A communications network comprises a lower transport layer and an upper overlay incorporating a plurality of routers. Adjacencies are defined between respective pairs of routers. Path protection is provided by defining a software model of the overlay of the network and defining in the model a hierarchy of protection levels for the main path. Each protection level is characterised by a respective set of one or more broken adjacencies in the model, the adjacencies to be broken being determined from a knowledge of the underlying topology. A protection level is selected and a protection path avoiding the broken adjacencies associated with that protection level is calculated. If this calculated path is not available in the real network, a lower protection level in the hierarchy is selected and the protection path calculation repeated. The process continues until a suitable protection path is identified.

Abstract: A communications packet network comprises a plurality of nodes interconnected by communication links and in which tunnels are defined for the transport of high quality of service traffic. The network has a set of primary traffic paths for carrying traffic and a set of pre-positioned recovery (protection) traffic paths for carrying traffic in the event of a fault affecting one or more the primary paths. The network incorporates a fault recovery mechanism. In the event of a fault, traffic is switched temporarily to a recovery path. The network then determines a new set of primary and recovery paths taking account of the fault. The traffic is then switched to the new primary paths. The new recovery paths provide protection paths in the event of a further fault. The network nodes at the two ends of a recovery path exchange information over that path so that packets returning to the main path present labels that are recognizable for further routing of those packets.