Lucent Technologies Inc.

Anwar Elwalid

Debasis Mitra

T V Lakshman

Robert H Wentworth

Martin May

This Generalized Processor Sharing (GPS) is the basis for the packet scheduler of choice in IP routers and ATM switches of the future. The currently accepted approach for the design of GPS schedulers is based on deterministic QoS guarantees, which, it is generally accepted, is overly conservative and leads to limitations on capacity. To address this problem we develop a framework for GPS scheduling which is based on statistical QoS guarantees and statistical multiplexing. We give the design of GPS weights which maximize the coverage of operating points, and also the design of the connection admission control (CAC). The general framework is end-to-end, with two heterogeneous QoS classes coexisting with a third, best effort class. Each QoS class has a specified delay bound together with a bound on the probability of its violation. An important objective is to maximize the bandwidth available to best effort traffic while just satisfying the guarantees of the QoS classes. To this end, we consider output regulated GPS scheduling which has the additional feature of limiting each connection's share of the bandwidth to a specified value, a design parameter which is determined by our analysis. The sources are subject to standard dual leaky bucket regulation. For the design of the GPS weights we give procedures based on two key concepts, the realizable set and the critical weights. The realizable set is the union of all admissible sets of connections of both classes over all weights. One of the main contributions is a pragmatic design process by which most of the realizable set is realized by only two critical weights. In the benign case, the system is &ldquo;effectively homogeneous&rdquo; and a single GPS weight suffices, while in the complementary &ldquo;effectively non-homogeneous&rdquo; case it is necessary to switch between the critical weights. The numerical results, which are for a single node with a wide range of traffic and QoS parameters, validate the design procedure and also show that there are substantial capacity gains from statistical multiplexing.

Packet scheduling in a communication network with statistical multiplexing of service classes

A packet network employing a reservation-based protocol system includes routers having processing sections that schedule message processing of the protocol's control messages adaptively based on link utilization. A scheduler of the processing section employs a round-robin scheduling with adaptive weight assignment to allocate processing capacity for control messages. For the RSVP protocol, for example, messages are grouped in classes, and link utilization of the packet flows for each message class is monitored. Weights corresponding to a portion of the processing section's processing capacity are allocated to each message class. The weights are defined based on link utilization for the message class and average message queue length. For processing sections monitoring multiple links, weights are further defined for super-classes based on overall link utilization. Weights may change as link utilization and average message size changes. With defined weights adaptively defined, the processing section then processes each message class in a cyclic, &ldquo;round-robin&rdquo; fashion.

Adaptive processor schedulor and method for reservation protocol message processing

The traffic shaping system according to the principles of the present invention increases the connection-carrying capacity of a network node by shaping the data cells to increase the admissible number of connections. In accordance with certain embodiments of the present invention, the traffic shaping system uses a data buffer at the ingress of the network node to selectively buffer classes of data cells. As such, the traffic shaping system exploits differences in delay tolerances between traffic classes to shape the less delay sensitive traffic classes to reduce the effective bandwidth of a connection of the particular traffic class and thereby increase the nodal connection-carrying capacity. Certain embodiments of the traffic shaping system operate within a framework to provide parameters for the traffic shaping system which increase the connection-carrying capacity for the node while meeting quality of service requirements for the data cells. In accordance with certain embodiments, an integrated regulator and shaper is provided which concurrently regulates and shapes the traffic cells to increase the nodal connection-carrying capacity.

Traffic shaper for network nodes and method thereof

A method regulates the admission control of, and requests for routing of, virtual circuits in a network by determining network resource requirements for the virtual circuits. In particular, the network resource requirements are based on a set of parameters used to control the flow of information from a communications device onto the virtual circuit. The requirements for network resources typically include buffer space requirements in network nodes and bandwidth requirements in network links, and the parameter used to control the flow of information are those associated with an access regulator. The network resource determination is made for the case where lossless performance in the network is required and in the case where statistical multiplexing with limited loss is allowed. Both constant bit rate and variable bit rate information is considered.

Method for admission control and routing by allocating network resources

An integrated method for congestion control uses access regulator to control the admission of information from a communication device into a network according to a predetermined function characterized by a set of parameters. A node within the network sends a signal indicating a level of congestion in the node to the access regulator, and at least one of the parameters is adjusted in response to the signal. The parameter may additionally be adjusted according to other parameters which are selected according to stability and transient response criteria.

Growing community of inventors

Murray Hill, NJ, United States of America

Anwar Elwalid