Nytell Software LLC

Other

Telcordia Technologies, Inc.

Telcordia Licensing Company, LLC

Sunil Samtani

Kirk K Chang

John Sucec

Gi Tae Kim

John Unger

John Lee

Rajesh Rasik Talpade

Harshad Tanna

Sumit Khurana

Larry H Wong

Petros Mouchtaris

In a secure network where the network characteristics are not known, a call admission control algorithm and a preemption control algorithm based on a destination node informing the source node of the observed carried traffic are used to regulate the amount of traffic that needs to be preempted by the source. The amount of traffic that needs to be preempted is based on the carried traffic measured at the destination node. The traffic to be preempted is based on the priority of the traffic, where the lowest priority traffic is the first to be preempted until the amount of traffic preempted is sufficient to allow the remaining traffic to pass through the network without congestion.

Call admission control and preemption control over a secure tactical network

Without using additional probing packets, estimates of the narrow link bandwidth and available bandwidth of a network path are computed based on existing traffic. The network can be of different types such as a wireless battlefield network context or a wired or wireless commercial network environment. 'Fast packets', i.e. those packets which do not experience any queuing delay in the network, are identified. Fast packets are identified to resolve end-to-end packet delay into its constituent components (deterministic, transmission and queuing delays), estimate path utilization and eliminate the uncertainty (false alarms) that causes the prior art method to lose its effectiveness. An estimation algorithm computes end-to-end transmission delay and end-to-end deterministic delay of fast packets traveling along a path in a network. Examples of deterministic delay include satellite propagation delays and clock effects. Then, based on the results of the fast packet identifying algorithm, two logic branches are followed. A first branch calculates utilization and a second branch calculates narrow link bandwidth. The narrow link bandwidth is determined from the packet pair dispersion. The available bandwidth is obtained from the narrow link bandwidth and the utilization. Estimation of available bandwidth for an end-to-end network path allows traffic sources to judiciously regulate the volume of application traffic injected into the network.

Estimating available bandwidth and enhancing narrow link bandwidth estimations in telecommunications networks using existing user traffic

Bandwidth allocated between the traffic classes of a network path is dynamically reallocated when one or more traffic classes have insufficient available bandwidth to support a service request for the traffic classes, wherein the reallocation occurs without modifying the traffic class bandwidth allocations enforced by router mechanisms. A provisioning system maintains an available bandwidth indication for each traffic class, which indications are decremented as a service request is admitted to the path. If a requested traffic class has insufficient available bandwidth to support a request, one or more other traffic classes can loan bandwidth to the requested traffic class by decrementing the available bandwidth indicators for the one or more other traffic classes in the amount of the insufficiency, thereby indicating that less bandwidth is available in these classes for future requests. The provisioning system also maintains an indication of the amount of bandwidth each traffic class loans to the other traffic classes.

Dynamic bandwidth reallocation

Methods and systems are provided for provisioning a network by identifying the classes of traffic to be transported in the network as well as the QoS criteria of the identified classes of traffic. By simulating the classes of traffic, one or more QoS mechanisms and their associated parameters may be determined. The statistical multiplexing gains of the classes of traffic may also be determined based on the simulation. Then, one or more resources in the network may be allocated based on the QoS mechanisms and parameters as well as the multiplexing gains.

Method and system for quality of service provisioning for IP virtual private networks

Growing community of inventors

East Newark, NJ, United States of America

Sunil Samtani