Abstract: Traffic measurement should make it possible to obtain the spatial flow of traffic through the domain, i.e., the paths or trajectories followed by packets between any ingress and egress point of the domain. A method of sampling packet trajectories in a packet switching network allows the direct inference of traffic flows through a measurement domain by observing the trajectories of a subset of all packets traversing the network. A method which assumes that the measurement domain does not change comprises the steps of selecting packets for sampling in accordance with a sampling function of the packet content and generating a practically unique label for each sampled packet. The method does not rely on routing state, its implementation cost is small, and the measurement reporting traffic is modest and can be controlled precisely. Using the same hash function will yield the same sample set of packets in the entire domain, and enables us to reconstruct packet trajectories.

Abstract: Traffic measurement should make it possible to obtain the spatial flow of traffic through the domain, i.e., the paths or trajectories followed by packets between any ingress and egress point of the domain. A method of sampling packet trajectories in a packet switching network allows the direct inference of traffic flows through a measurement domain by observing the trajectories of a subset of all packets traversing the network. A method which assumes that the measurement domain does not change comprises the steps of selecting packets for sampling in accordance with a sampling function of the packet content and generating a practically unique label for each sampled packet. The method does not rely on routing state, its implementation cost is small, and the measurement reporting traffic is modest and can be controlled precisely. Using the same hash function will yield the same sample set of packets in the entire domain, and enables us to reconstruct packet trajectories.

Abstract: A system and method are provided for a scalable and efficient multipoint-to-multipoint multicast in packet and sub-packet based communications networks. The methodology of the invention incorporates an additional switching feature called cut-through forwarding, which enables the mapping of several incoming virtual channels into one or several outgoing virtual channels. The inventive methodology further provides a shared tree spanning all senders and receivers of the multicast group. Centrally initiated group setup as well as dynamic group membership changes are incorporated into the invention. An additional feature of the invention, designated “short-cutting”, allows for the transmission of a packet to follow the shortest path along the shared tree.

Abstract: A data transmission system and method employing either a renegotiated variable bit-rate ("RVBR") network or a renegotiated constant bit-rate ("RCBR") network. Within these networks, data transmission rates between a sender and a recipient are rapidly renegotiated as a function of previously stored data transmission rate information and system buffer levels. Such a system and method can be readily implemented within existing CBR and/or VBR network architectures. The RCBR and RVBR networks allow for the implementation of an intelligent data traffic management systems that are responsive to the rate at which new calls or requests for connections enter and leave the network, the frequency and duration of extended peak rate data bursts, as well as the occurrence of short duration data transmission peaks.

Abstract: A system and method for the segmentation of data exhibiting an intrinsic long-term average data rate, punctuated with periods of peak rate data bursts. This segmentation conditions the data for efficient transmission via either a renegotiated constant bit-rate ("RCBR") network or a renegotiated variable bit-rate network ("RVBR") network. Within these networks, data transmission rates between a sender and a recipient are rapidly renegotiated as a function of previously stored data transmission demand information and system buffer levels. Such a system is responsive to the rate at which new calls or requests for connections enter and leave the network, the frequency and duration of extended peak rate data bursts, as well as the occurrence of short duration data transmission peaks.