Abstract: Modifying quality of service treatment for data flows A method of transmitting a data flow via a network is disclosed where the network supports transmission of data in accordance with a plurality of Quality of Service, QoS, models. Prior to transmission of the data flow, a client system configures a first class of service for the data flow based on a first QoS model, and a first portion of the data flow is transmitted through the network in accordance with the first class of service. In response to detecting a renegotiation condition, the network communicates with the client system to configure a second class of service for the data flow based on a second QoS model, and a subsequent portion of the data flow is transmitted through the network using the second class of service.

Abstract: The present invention provides a computer implemented method for allocating resources to Quality of Service, QoS, models in a network, the method comprising: selecting a route in the network, wherein the route comprises a plurality of flows of network traffic; obtaining model-to-route mapping data identifying a plurality of QoS models, wherein each QoS model is used by at least one of the plurality of flows of network traffic; monitoring the plurality of flows of network traffic to determine a characteristic of each of the plurality of flows; and in the event that one of the QoS models is withdrawn, reallocating resources of the selected route to flows of network traffic along that route, wherein the reallocation is based on at least one of: the QoS model used by each of the flows of network traffic along that route; and the characteristic of each of the flows.

Abstract: A method of allocating resources in a network for the transmission of a data flow is disclosed. The method involves receiving a query specifying one or more quality-of-service (QoS) requirements for the data flow and identifying, based on the specified QoS requirements, one or more QoS models from a set of stored QoS models, each QoS model defining a class of service available in the network. A query response specifying the identified QoS models is transmitted. Subsequently, a reservation request is received specifying at least one of the identified QoS models. Resources are allocated in the network for the data flow based on the at least one QoS model specified in the reservation request.

Abstract: The present invention provides a method of providing QoS models for a communications network in which: data is obtained data describing a plurality of QoS models, with each QoS model containing at least one QoS component specifying a characteristic of network traffic to be provided by the QoS model; monitoring network traffic to obtain a plurality of indicators, each indicating a characteristic of the network traffic associated with one of the QoS models; selecting, based on the indicators, a subset of the plurality of QoS models; and providing data identifying the subset of QoS models to a client device to enable the client device to send data over the network according to a selected one of the subset of QoS models.

Abstract: A network management method is described for managing energy utilisation in a network comprising network elements that handle network traffic. The network elements are analysed to identify at least one candidate network element for energy usage reduction. Routes passing through the candidate network element are then identified and at least one alternative route is identified for each identified route. Each identified route is switched onto the at least one alternative route, wherein the alternative route does not pass through the original candidate network element. Finally, the candidate network element is triggered to enter a lower power mode. In a particular embodiment, a quality of service level associated with each identified route is determined and the method ensures that the alternative route has an associated quality of service level equal to or better than the original quality of service level. Systems and apparatus for implementing the method are also described.

Abstract: The present invention provides a method of operating a communications network such that the classes of service offered by a network operator will depend upon the underlying conditions in the network. A number of performance models, each of which is described by two vectors, is determined from historical network data. These performance models can be assigned to routes through the communications network, such that a request for a session can be made in accordance with the offered performance model for that route.

Abstract: The present invention provides a method comprising: receiving a plurality of queries, each query specifying one or more quality-of-service (QoS) requirements for the transmission of a data flow in a network; determining a query prototype, the query prototype comprising at least one QoS component value based on the one or more QoS requirements; obtaining a plurality of items of route data, wherein each item of route data is associated with a corresponding route through the network and indicates a QoS component of the corresponding route; comparing the route data with the query prototype to identify routes which match the query prototype; and in the event that a selected number of routes match the query prototype, responding to a further query by transmitting a query response comprising a new QoS model based on the matching query prototype.

Abstract: A method of operating a communications network, in which a primary learning process periodically determines which routes communications sessions are assigned to in order that the session can be carried with a requested QoS. A secondary learning process is used, in between instances of the primary learning process to check that the QoS constraints are still satisfied. If not, action is taken, for example using a load balancer to transmit the session over one or more further network routes.

Abstract: Methods and apparatus for determining and using link performance measures (DL, CL) in respect of communication links (125) in a cata communication network (100) are disclosed, where the network comprises a plurality of data-forwarding nodes (120) each capable of forwarding data along a plurality of communication links (125). Link performance measures (DL, CL) are determined in dependence on end-to-end path performance measures (Es,u) received in respect of a plurality of end-to-end paths having at least one link in common, and on the basis of route information (Rs,u) identifying the links of which those end-to-end paths are comprised. Methods are disclosed for using link performance measures in relation to decisions regarding the routing and/or re-routing of data in a network, and in relation to determining measures indicative of expected quality of experience in respect of data traversing end-to-end paths across a network.

Abstract: The servers in a data network are monitored (16) and classified (290) according to the data flows to and from the servers, to identify servers with low usage, and programming instructions and data relating to those servers are retrieved and stored (32, 17) so that they may subsequently be retrieved (18) to replicate the server to which they relate.

Abstract: Method and systems for managing QoS models for traffic flows in a network are described. In particular, the method includes storing the QoS models and analyzing at least one of the QoS models to determine whether the QoS model satisfies a suitability test. One or more QoS models are then selected based on the analysis and these selected models are offered to a client for use with a traffic flow in the network. In one embodiment, the method may be implemented based on a query from a client requesting reservation of network resources for a traffic flow. The analysis may be based on a characteristic of the or each QoS model, of the client, of a query received from the client requesting reservation of network resources for the traffic flow or of the network or an operator of the network.

Abstract: There are described methods and systems for distributing content in a network, in particular a multicast network. One method includes delivering content from a source to a destination in a content delivery network. A request for an item of content is received and a first multicast stream is identified or established, the first multicast stream comprising a first copy of the content. At least one second multicast stream is also identified or established, the second stream comprising a second copy of the content. The second copy of the content is time-shifted by a time, M, from corresponding portions of the first copy of the content. The content is then delivered to the destination using both the first and the second multicast streams.

Abstract: There is described a method of managing routing paths, in particular multicast routing paths, in a content delivery network. The method includes determining, according to a unicast routing protocol, a first link cost for a first routing path and determining a second link cost for a second routing path, the second routing path comprising a first component comprising a link cost to a router that is part of a multicast group and a second component comprising a link cost for the multicast tree from the router. An adjustment factor is then determined based on information received from the content delivery network. The adjustment factor is applied to the second link cost. The adjusted second link cost and the first link cost are analyzed to determine an adjusted least cost path in the content delivery network and the adjusted second link cost is selectively output to a routing database to influence routing in the content delivery network.

Abstract: There are described methods and systems for distributing content in a network, in particular a multicast network. One method includes delivering content from a source to a destination in a content delivery network. A request for an item of content is received and a first multicast stream is identified or established, the first multicast stream comprising a first copy of the content. At least one second multicast stream is also identified or established, the second stream comprising a second copy of the content. The second copy of the content is time-shifted by a time, M, from corresponding portions of the first copy of the content. The content is then delivered to the destination using both the first and the second multicast streams.

Abstract: There are described methods and systems for distributing content in a network, in particular a multicast network. One method includes delivering content from a source to a destination in a content delivery network. A request for an item of content is received and a first multicast stream is identified or established, the first multicast stream comprising a first copy of the content. At least one second multicast stream is also identified or established, the second stream comprising a second copy of the content. The second copy of the content is time-shifted by a time, M, from corresponding portions of the first copy of the content. The content is then delivered to the destination using both the first and the second multicast streams.

Abstract: A method of distributing content from a source in a content delivery network, the method comprising: monitoring requests for delivery of an item of content; obtaining a prediction of future demand in respect of the said content; applying a unicast-to-multicast switching decision algorithm, the switching decision algorithm taking into account the prediction of future demand and arranged to determine whether at least one trigger condition is met; and, dependent on the outcome of the unicast-to-multicast switching decision algorithm, initiating the transition of a plurality of unicast data streams to a multicast data stream in respect of the item of content.

Abstract: There are described methods and systems for distributing content in a network, in particular a multicast network. One method includes delivering content from a source to a destination in a content delivery network. A request for an item of content is received and a first multicast stream is identified or established, the first multicast stream comprising a first copy of the content. At least one second multicast stream is also identified or established, the second stream comprising a second copy of the content. The second copy of the content is time-shifted by a time, M, from corresponding portions of the first copy of the content. The content is then delivered to the destination using both the first and the second multicast streams.

Abstract: The servers in a data network are monitored (16) and classified (290) according to the data flows to and from the servers, to identify servers with low usage, and programming instructions and data relating to those servers are retrieved and stored (32, 17) so that they may subsequently be retrieved (18) to replicate the server to which they relate.

Abstract: The present invention provides a method of providing QoS models for a communications network in which: data is obtained data describing a plurality of QoS models, with each QoS model containing at least one QoS component specifying a characteristic of network traffic to be provided by the QoS model; monitoring network traffic to obtain a plurality of indicators, each indicating a characteristic of the network traffic associated with one of the QoS models; selecting, based on the indicators, a subset of the plurality of QoS models; and providing data identifying the subset of QoS models to a client device to enable the client device to send data over the network according to a selected one of the subset of QoS models.

Abstract: A method of allocating resources in a network for the transmission of a data flow is disclosed. The method involves receiving a query specifying one or more quality-of-service (QoS) requirements for the data flow and identifying, based on the specified QoS requirements, one or more QoS models from a set of stored QoS models, each QoS model defining a class of service available in the network. A query response specifying the identified QoS models is transmitted. Subsequently, a reservation request is received specifying at least one of the identified QoS models. Resources are allocated in the network for the data flow based on the at least one QoS model specified in the reservation request.