Abstract: A computer implemented method performed by a node in a communications network comprises obtaining Key Performance Indicator, KPI, targets for a plurality of KPIs, in the communications network, and determining relationships between the KPIs using a model trained using a graph-based machine learning process. Each relationship describes a manner in which changing a network configuration to alter a first one of the plurality of KPIs affects a second one of the plurality of KPIs. The method then comprises determining one or more conflicts between the KPI targets, using the relationships.

Abstract: There is provided a method performed by an entity for managing connectivity of a device to a network. The method comprises selecting, from a plurality of connectivity service providers in the network, a connectivity service provider (CSP) to connect the device to the network. The selection is based on information about the device.

Abstract: A computer implemented method performed by a node in a communications network comprises obtaining Key Performance Indicator, KPI, targets for a plurality of KPIs, in the communications network, and determining relationships between the KPIs using a model trained using a graph-based machine learning process. Each relationship describes a manner in which changing a network configuration to alter a first one of the plurality of KPIs affects a second one of the plurality of KPIs. The method then comprises determining one or more conflicts between the KPI targets, using the relationships.

Abstract: A method performed by a first node in a communications network for use in training a model using a machine learning process using Hybrid Automatic Repeat Request, HARQ, transmissions. The method includes reserving HARQ resources between a second node and a third node in the communications network for training of the model. The method further includes initiating a first test transmission from the second node to the third node using the reserved HARQ resources in order to obtain data with which to train the model.

Abstract: A method and a controller for handling a failure or change of a processing element in a virtual network are provided. The processing element includes a first stateless executable function that use a local state storage and a persistent state storage when executed on a host in the virtual network. The controller maintains the local state storage of the processing element upon removing the first stateless executable function from the processing element in response to the failure or change. The controller also creates a second stateless executable function to replace the first stateless executable function in the processing element. Then, the controller associates the maintained local state storage with the second stateless executable function for the processing element. Further, the controller initiates the second stateless executable function using the associated maintained local state storage such that the processing element resumes execution from its real-time state before the failure or change.

Abstract: A method performed by a first node in a distributed network is provided. The method includes receiving a request from a second node for transfer learning of a machine learning model for a use case. The request includes a description of a local environment and a use case identifier at the second node. The method further includes identifying a matching criteria for the local environment of the second node based on the use case. The method further includes determining whether at least one distributed node from a plurality of distributed nodes in the distributed network satisfies at least one of a match or a closest match to the matching criteria.

Abstract: Methods, apparatuses and computer programs are disclosed. The method of allocating network resources to a plurality of media flows in a communications network, the method comprising the steps of: determining a media content characteristic for the plurality of media flows; partitioning the plurality of media flows into one or more media flow groups based on the media content characteristic; initiating allocation of a separate network resource pool to the one or more media flow groups to be used by media flows belonging to respective media flow group.

Abstract: A computer implemented method performed by an application programming interface (APIR) for a network node in a radio access network is provided. The APIR for the network node can receive a request from a data processing entity to transition to a defined network operating condition in the radio access network. The APIR for the network node can further transition to the defined network operating condition during a defined time period. The APIR for the network node can further collect data during the defined time period including at least one observation of the defined network operating condition, an action in the radio access network during the defined network operating condition, and a subsequent observation of the radio access network based on the action. A method performed by a data processing entity is also provided.

Abstract: A node in a communications network is configured to use a reinforcement learning agent to manage a process associated with the communications network. The node is further configured to adjust a value of an exploration rate associated with training of the reinforcement learning agent, based on a performance indicator associated with the managed process.