Abstract: In a method in a user equipment, UE, in a communications network, of determining whether to perform a handover procedure from a first network node to a second network node, a location of the UE is provided as input to a model stored on the UE, the model having been trained using a machine learning process to predict conditions on the second network node in the communications network based on the location of the UE. A prediction of conditions on the second network node at the provided location of the UE is provided by the model. The received predicted conditions are then used to determine whether to perform a handover procedure.

Abstract: A method performed by a first wireless device served by a first wireless access point in a first wireless communications network, the first wireless communications network being operated by a first network operator, comprises acquiring (202) a determination from a first reinforcement learning agent of whether to roam from the first wireless access point to a second wireless access point in a second wireless communications network, the second wireless communications network being operated by a second network operator. The method further includes roaming (204) from the first wireless access point to the second wireless access point, based on the determination.

Abstract: Some embodiments herein relate to a method performed by a wireless communication device for managing communication in a wireless communications network. The wireless communication device obtains an indicator indicating a model and one or more trained model parameters for the model, wherein the model is related to an event being one of the following events: a handover procedure, a cell reselection procedure, and a beam reselection procedure. The wireless communication device further selects the model based on the obtained indicator. The wireless communication device executes the selected model using the obtained one or more trained model parameters; and triggers a process, being associated with the event, based on an output of the executed model.

Abstract: A computer implemented method of training a reinforcement learning model for controlling a dynamic system includes generating a trajectory sample of a simulated system that corresponds to the dynamic system, the trajectory sample including a current state st of the simulated system at time t, an action at taken on the simulated system at time t according to a policy ?, a subsequent state st+1 of the simulated system following the action at, and a reward r associated with the action at, and estimating a robust target value V?(st) for the trajectory sample, wherein the robust target value V?(st) includes an expected value of a sum of the reward r and a minimum estimated value V?(st+1) of the simulated system at the subsequent state st+1 based on a plurality of transition possibilities p from the current state st in response to the action at. The method updates a value function estimator based on the robust target value, and updates the policy based on the trajectory and the value function estimator.

Abstract: Embodiments of the disclosure provide methods, apparatus and computer programs for generating a radio coverage map. A method comprises: obtaining image data of a geographical area, the image data comprising: a representation of the environment in the geographical area; and an indication of one or more transmission point locations corresponding to the locations of one or more transmission points in a wireless communications network; and applying a generative model to the image data, to generate a radio coverage map of the geographical area.

Abstract: A method performed by a first network entity in a communications network is provided. The method comprises receiving a request from a second network entity, the request comprising one or more selection criteria for selecting network entities to participate in a collaborative learning process to train a model using a machine learning algorithm. The method further comprises transmitting a response message comprising an indication of whether or not the first network entity satisfies the one or more selection criteria.

Abstract: A method performed by a first network entity in a communications network includes training a model to obtain a local model update including an update to values of one or more parameters of the model, in which training the model includes inputting training data into a machine learning algorithm. The method further includes applying a serialisation function to the local model update to construct a serial representation of the local model update, thereby removing information indicative of a structure of the model, and transmitting the serial representation of the local model update to an aggregator entity in the communications network.

Abstract: A method performed by a co-ordination network entity in a communications network includes transmitting a request message to a network registration entity in the communications network for identification information for a plurality of candidate network entities in the communications network capable of performing collaborative learning, and receiving identification information for the plurality of candidate network entities from the network registration entity. The method further includes initiating, at one or more network entities of the plurality of candidate network entities, training of a model using a machine-learning algorithm as part of a collaborative learning process.

Abstract: A method performed by a first entity in a communications network is provided. The first entity belongs to a plurality of entities configured to perform federated learning to develop a model. In the method, the first entity trains a model using a machine-learning algorithm, generating a model update. The first entity generates a first mask, receives an indication of one or more respective second masks from a subset of the remaining entities of the plurality of entities, and combines the first mask and the respective second masks to generate a combined mask. The first entity transmits an indication of the first mask to one or more third entities of the plurality of entities. The first entity applies the combined mask to the model update to generate a masked model update and transmits the masked model update to an aggregating entity of the communications network.

Abstract: A method for creating one or more machine learning models in a model training engine is provided. The method includes providing to a user, via a graphical user interface, a selection of components for a machine learning model, at least one component having a computational layer including one or more coefficients associated with a component attribute. The method also includes displaying, in the graphical user interface, a component selected by the user, including a selected value of the component attribute and executing the machine learning model with a training archive as an input, to obtain an output indicative of a desired feature of the training archive. The method also includes comparing the output with a desirable feature value, and modifying at least one coefficient in the component of the machine learning model based on a difference between the output from the machine learning model and the desirable feature value.

Abstract: The present invention relates to a method for predicting a performance indicator for a service in a network. The method is performed by a network node of the network, and the method comprises obtaining measurement data of a metric affecting a service communicating via a radio access network, RAN, node, wherein the metric is independent of the service communicating via the RAN node, inputting the obtained measurement data into a prediction model for performance of the service communicating via the RAN node, wherein the prediction model has been trained with measurement data from the RAN node and measurement data from an end node, and predicting the performance indicator for performance of the service in the network. A network node, a computer program and a computer program product are also presented.

Abstract: The present invention relates to a method for predicting a performance indicator for a service in a network. The method is performed by a network node of the network, and the method comprises obtaining measurement data of a metric affecting a service communicating via a radio access network, RAN, node, wherein the metric is independent of the service communicating via the RAN node, inputting the obtained measurement data into a prediction model for performance of the service communicating via the RAN node, wherein the prediction model has been trained with measurement data from the RAN node and measurement data from an end node, and predicting the performance indicator for performance of the service in the network. A network node, a computer program and a computer program product are also presented.

Abstract: Some embodiments herein relate to a method performed by a wireless communication device for managing communication in a wireless communications network. The wireless communication device obtains an indicator indicating a model and one or more trained model parameters for the model, wherein the model is related to an event being one of the following events: a handover procedure, a cell reselection procedure, and a beam reselection procedure. The wireless communication device further selects the model based on the obtained indicator. The wireless communication device executes the selected model using the obtained one or more trained model parameters; and triggers a process, being associated with the event, based on an output of the executed model.

Abstract: A method performed by a first wireless device served by a first wireless access point in a first wireless communications network, the first wireless communications network being operated by a first network operator, comprises acquiring (202) a determination from a first reinforcement learning agent of whether to roam from the first wireless access point to a second wireless access point in a second wireless communications network, the second wireless communications network being operated by a second network operator. The method further includes roaming (204) from the first wireless access point to the second wireless access point, based on the determination.

Abstract: Embodiments of the disclosure provide methods, apparatus and computer programs for generating a radio coverage map. A method comprises: obtaining image data of a geographical area, the image data comprising: a representation of the environment in the geographical area; and an indication of one or more transmission point locations corresponding to the locations of one or more transmission points in a wireless communications network; and applying a generative model to the image data, to generate a radio coverage map of the geographical area.

Abstract: The present invention relates to a method for predicting a performance indicator for a service in a network. The method is performed by a network node of the network, and the method comprises obtaining measurement data of a metric affecting a service communicating via a radio access network, RAN, node, wherein the metric is independent of the service communicating via the RAN node, inputting the obtained measurement data into a prediction model for performance of the service communicating via the RAN node, wherein the prediction model has been trained with measurement data from the RAN node and measurement data from an end node, and predicting the performance indicator for performance of the service in the network. A network node, a computer program and a computer program product are also presented.

Abstract: The present disclosure generally relates to the field of queue management. More specifically, the present disclosure relates to a technique of adjusting adaptive queue management operation in a wireless communication network. A method embodiment comprises determining (S202), by an access network node (100) of the wireless communication network, whether an increase in capacity for data transmission between the access network node (100) and a wireless communication device (300) is expected, and adjusting (S204), by the access network node (100), AQM operation associated with the access network node (100), if it is determined that an increase in capacity for data transmission between the access network node (100) and the wireless communication device (300) is expected.

Abstract: The present disclosure generally relates to the field of queue management. More specifically, the present disclosure relates to a technique of adjusting adaptive queue management operation in a wireless communication network. A method embodiment comprises determining (S202), by an access network node (100) of the wireless communication network, whether an increase in capacity for data transmission between the access network node (100) and a wireless communication device (300) is expected, and adjusting (S204), by the access network node (100), AQM operation associated with the access network node (100), if it is determined that an increase in capacity for data transmission between the access network node (100) and the wireless communication device (300) is expected.

Abstract: For controlling radio transmission in a cellular network, a network node detects data traffic between the cellular network and a user equipment. The detected data traffic is based on a transport protocol which involves transmission of an acknowledgement to acknowledge successful reception of data by the user equipment. The network node estimates a time at which sending of an future acknowledgement by the user equipment is expected. On the basis of the estimated time, the network node allocates UL radio resources to the user equipment. By sending an uplink grant, the network node may indicate the allocated uplink radio resources to the user equipment.

Abstract: For controlling radio transmission in a cellular network, a network node detects data traffic between the cellular network and a user equipment. The detected data traffic is based on a transport protocol which involves transmission of an acknowledgement to acknowledge successful reception of data by the user equipment. The network node estimates a time at which sending of an future acknowledgement by the user equipment is expected. On the basis of the estimated time, the network node allocates UL radio resources to the user equipment. By sending an uplink grant, the network node may indicate the allocated uplink radio resources to the user equipment.