Nortel Networks Corporation

Northern Telecom Limited

Notel Networks Corporation

Peter G Hamer

Paul Anthony Kirkby

Phillip William Hobson

Kevin John Twitchen

David Ireland

Timothy John Edwards

Paul Colin Barson

Simon Field

Kevin John Warbrick

Michael Heffernan

Malcolm Edward Carter

Radhakrishnan Kadengal

Jonathon Coward

Jon Weil

Richard Clegg

Arthur Clune

Admission of rapidly varying traffic flows to a communications network is controlled by sampling the traffic flows each at an ingress, and sampling an aggregate flow of said flows at some or all of the resources used by the aggregate flow. From this sampling, a mean bandwidth requirement for each traffic flow and a measure of the variance from that mean are determined. First and second prices for the mean and variance components of the controlled traffic flows that are calculated. These price calculations are used to determine an admission cost for each said flow so as to regulate the admission of that flow via a feedback price mechanism.

Traffic flow management in a communications network

A communications network has multiple resource-allocation layers and incorporates a management structure for allocating resources to allocate resources requested by a first layer of said layers from a second of said layers. At a first layer, the management structure provides an indication to a second layer of the required resources that are to be allocated from the second layer. The second layer automatically offers the required resource together with a condition for use of those resources. This condition includes a notional price factor which is dependent on current demand. Under the control of the manager, the first layer determines if the condition for use of the offered resources is acceptable and, if so, automatically accepts the offered resources from the second layer. In a preferred embodiment, ingress to an underlying multi-wavelength transport layer of the network is controlled via a virtual port which allocates traffic to real ports one for each wavelength supported by the transport layer.

Management and control of multi-layer networks

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.

Reducing network traffic congestion

Internet protocol based transmissions have historically been transmitted on a best efforts basis. There are proposals to provide differentiated services to allow different packets to be delivered with different service qualities depending on the bandwidth requirements of a particular flow. By performing bandwidth monitoring within the core network and performing packet dropping and/or queuing at the network ingress, the need for packet dropping and/or queuing within the core network is removed and furthermore the core network resources are not used by packets which will not be delivered to their destination but will instead be dropped within the core network.

Differentiated services in packet-switched networks

A method of predicting at least one future value of a time series of data using a neural network comprising the steps of:

Method and apparatus for forecasting future values of a time series

A method of managing the processing of information using a first neural network, the information relating to the transmission of messages in a telecommunications network, uses the steps of:

Monitoring and retraining neural network

A generic anomaly detection engine is described which provides neural network technology to process information such as call detail records and detect anomalies in the information, such as mobile phone fraud. Information from call detail records is pre-processed to form signatures which represent the calling behavior of a subscriber. These signatures are formed in one of a plurality of predetermined formats. The generic anomaly detection engine is instantiated in order to create an anomaly detector which is suitable for a particular situation and during the instantiation process the topology of the neural network components is automatically adjusted to fit the required situation. The topology is adjusted to according to the format of the signatures.

Growing community of inventors

Herts, United Kingdom

Peter G Hamer