International Business Machines Corporation

Motorola Corporation

Levent Gun

Roch A Guerin

Gerald Arnold Marin

Hamid Ahmadi

Jeffrey Haskell Derby

Lap Thiet Huynh

John E Drake, Jr

Richard B Kline

Krishnan Ramakrishnan

Theodore E Tedijanto

Claude R Galand

Ken Van Vu

Allen Leonid Roginsky

Mahmoud Naghshineh

Raif O Onvural

Jeane S Chen

Chee-Seng Chow

Bouchung Lin

Chester A Ruszczyk

Philip F Chimento, Jr

Khosrow Sohraby

Jeffrey, H Derby

Vidyadhar G Kulkarni

Anthony M Lee

Rong-Feng Chang

An enhanced adaptive rate-based congestion control system for packet transmission networks uses the absolute rather than the relative network queuing delay measure of congestion in the network. Other features of the congestion control system include test transmissions only after a predetermined minimum time, after the receipt of an acknowledgment from the previous test, or transmission of a minimum data burst, whichever takes longest. The congestion control system also provides a small reduction in rate at low rates and a large reduction in rates at high rates. A logarithmic rate control function provides this capability. Rate damping is provided by changing all of the values in a rate look-up tables in response to excessive rate variations. Finally, the fair share of the available bandwidth is used as the starting point for rates at start-up or when a predefined rate damping region is exited.

Adaptive rate-based congestion control in packet networks

A cell based network (100) for transmitting ATM user cells (118), including ABR data cells (118.sub.D) and forward control, or RM, cells (118.sub.FRM) at predetermined cell rates from at least one user source (102) in a virtual connection (VC, 110) through at least one ATM switch (120) and at least one transmission link (130) in the network to at least one user destination (104), employs a method and apparatus for controlling a user source (102) transmission cell rate in the presence of congestion in the VC (110). The calculation of a Fair Share cell transmission rate is written into a backward control, or RM, cell (118.sub.BRM) optionally takes place only in the presence of congestion at an ATM Switch (120). The calculation of the Fair.sub.-- Share value is simplified and calculation time is shortened by changing the number of active ABR VCs (N.sub.ABR) to a factor of two (E.sub.NABR) and dividing the maximum cell transmission rate by E.sub.NABR.

Simplified calculation of cell transmission rates in a cell based netwook

A cell based network (100) for transmitting cells (118), including data cells and control cells at predetermined cell rates from at least one user source (102) in a virtual connection, VC (110), through at least one switch (120) and at least one transmission link (130) in the network to at least one user destination (104) employs a method for controlling a user source (102) transmission cell rate in the presence of congestion in the VC (110). The calculation of a Fair.sub.-- Share value of the Explicit Rate (ER) that is written into a backward control cell takes place only in the presence of congestion at either an Ingress Switch Port (141) or on an Egress Physical Port (162) connected to the Switch (120).

Method and apparatus for controlling cell transmission rate in a cell

The entry polling (EP) method (900) of the present invention primarily incorporates two types of polling: contention based and standard polling. The present invention provides several advantages over present polling approaches. EP slots allow multi-priority users to compete for access into the standard polling scheme. The reservation channel is efficiently used by dynamically adjusting the frequency of contention slots based on system dynamics and dynamically changing the number of contention minislots for each service category within a contention slot with the case of sending only one minislot per slot. The channel is assigned primarily to active users. Pipeline polling is also incorporated, thus providing full use of the upstream channel. Since the local state information is provided by the user, the central controller may allow multiple variable length packets to be sent.

Method, device and router for providing a contention-based reservation

A packet communications network is adapted for efficiently handling of multi-priority traffic (such as multi-media traffic) by defining an access algorithm that not only ensures the requested loss probabilities for both priorities of traffic, but also optimizes the bandwidth required to carry both priority classes. A buffer having a properly sized occupancy threshold admits high priority traffic if there is room in the buffer, but admits lower priority traffic only if the buffer occupancy is below the occupancy threshold. The resulting consolidated multi-priority traffic can then be characterized by an effective bandwidth which increases the packet network capacity substantially. The multi-priority access mechanisms require little or no changes in the prior art access mechanisms and utilize pre-existing leaky bucket, route selection and link metric mechanisms of the prior art.

Traffic management in packet communications networks

An end-to-end, closed loop flow and congestion control system for packet communications networks exchanges rate request and rate response messages between data senders and receivers to allow the sender to adjust the data rate to avoid congestion and to control the data flow. Requests and responses are piggy-backed on data packets and result in changes in the input data rate in a direction to optimize data throughput. GREEN, YELLOW and RED operating modes are defined to increase data input, reduce data input and reduce data input drastically, respectively. Incremental changes in data input are altered non-linearly to change more quickly when further away from the optimum operating point than when closer to the optimum operating point.

Adaptive rate-based congestion and flow control in packet communications

Access control for a packet communications network includes a dynamic bandwidth updating mechanism which continuously monitors the mean bit rate of the signal source and the loss probability of the connection. These values are filtered to remove noise and then used to test whether the values fall within a pre-defined acceptable adaptation region in the mean bit rate, loss probability plane. Values falling outside of this region trigger bandwidth updating procedures which, in turn, result in acquiring a new connection bandwidth, and determining new filter parameters and new parameters for a leaky bucket access mechanism.

Dynamic bandwidth estimation and adaptation for packet communications

In a packet communications network, the addition or deletion of a connection to the network by a user is governed by a link traffic metric which represents the effective capacity of each link in the network which participates in the packet connection route. A new connection (or deletion) is represented by a compatible metric which allows updates in the link metric by simple vector addition or subtraction. Separate link metrics for a plurality of classes of service permit a much higher efficiency in the exploitation of the link bandwidth than is possible with a single link metric. A packet network using multiple link metrics and efficient metric updating techniques provides increased packet throughput while, at the same time, preserving all class of service guarantees.

A congestion control system for packet communications networks in which access to the network is controlled to prevent such congestion. Packets within the prespecified statistical description of each packet source are marked as high priority ('green' packets) while packets exceeding the pre-specified characteristics are marked with a lower priority ('red' packets). The overall red packet rate is limited to prevent red packet saturation of the network. Packets are marked red for a continuous train of successive red packets. The introduction of red packets into the network is subjected to a degree of hysteresis to provide better interaction with higher layer error recovery protocols. The amount of hysteresis introduced into the red packet marking can be fixed or varied, depending on the statistics of the incoming data packets at the entry point to the network.

Rate-based congestion control in packet communications networks

In a packet communications network, the addition or deletion of a connection to the network by a user is governed by a link traffic metric which represents the effective capacity of each link in the network which participates in the packet connection route. The link metric is calculated in real-time and updated by simple vector addition or subtraction. Moreover, this link metric is also used to calculate leaky bucket parameters which govern the access of packets to the network once the connection is set up. A packet network using these link metrics and metric generation techniques provides maximum packet throughput while, at the same time, preserving grade of service guarantees.

A packet communications network relies on a few simple parameters to characterize the wide variety of traffic offered to that network, such as peak bit rate, mean bit rate and average packet burst length. A better representation of many types of traffic relies on an equivalent burst length which produces the same loss probability distribution, but assumes that the distribution is uncorrelated and exponential. Access control and bandwidth management based on such an equivalent burst length produces improved decisions due to the more accurate representation of the actual traffic distribution.

Traffic measurements in packet communications networks

A packet communications system utilizes a route determining mechanism by identifying principal paths between the source and the destination in the system. Principal paths are minimum hop count paths with a transmission delay less than a specified threshold. Principal path links are accepted as legs of the optimum path, if feasible, i.e., if the resulting load on the link is less than a specified principal threshold. Secondary links are accepted only if the resulting load on the link is less than a specified secondary threshold, where the secondary threshold is less than the principal threshold. All paths must also have a transmission delay less than a specified threshold. Each request for a route includes the source node, the destination node, the load required, the maximum transmission delay and, if desired, the quality of service parameters which all of the legs of the route must satisfy. A modified Bellman-Ford breadth-first search algorithm is used to identify the principal links and, using these principal link identifications, determining the optimum path.

Growing community of inventors

Durham, NC, United States of America

Levent Gun