Abstract: The disclosure provides methods, apparatus and machine-readable mediums for mitigating power failures in base stations in wireless communication networks. In one aspect of the disclosure, a method for mitigating power failures in a wireless communication network is provided. The method comprises, responsive to a determination that a primary power supply for a base station in the wireless communication network has failed or is predicted to fail, initiating deployment of an unmanned aerial vehicle to the base station to charge one or more batteries providing a secondary power supply for the base station.

Abstract: A method performed by a content server (100) for determining additional media content to be inserted into a main media content wherein the main media content is in a virtual environment, the method comprising: acquiring (S201) information relating to a user profile of each of a plurality of users that are viewing the main media content; clustering (S202) the plurality of users into one or more user clusters based on the user profile of each of the plurality of users; acquiring (S203) a viewing state of each of the plurality of users that are viewing the main media content, wherein the viewing state of each of the plurality of users comprises biometric data of each of the plurality of users; acquiring (S204) information relating to a network quality; and determining (205) the additional media content for each of the plurality of users by a first reinforcement learning agent based on the one or more user clusters, the viewing state of each of the plurality of users, and the network quality.

Abstract: A method is provided. The method comprises obtaining local observation data of a group of one or more agents. The local observation data indicates performance of each agent included in the group. The method further comprises obtaining global state data indicating collective performance of the group and based on the obtained local observation data and the obtained global state data, determining a discount factor for each agent included in the group. The discount factor is a weight value of a future expected reward for each agent included in the group.

Abstract: A method manages a group of Unmanned Aerial Vehicles (UAVs) operable to fly in a formation. Each UAV is programmed with a task to be performed by the UAV. The method is performed in a controller UAV of the group and comprises receiving UAV status information from UAVs in the group, obtaining information on a current formation of the group and combining the received UAV status information with the information on current group formation to form a representation of a first state of the group. A machine learning model is used to predict, based on the first state of the group, an optimal formation transition to a new formation and to instruct the UAVs in the group to perform the predicted optimal formation transition, which is a transition to a formation that will minimise predicted total energy consumption for all UAVs in the group to complete their tasks.

Abstract: A method performed by a communication device in a communication network for augmenting a communication signal message with environmental information relative to the communication device is provided. The method includes performing a first reference signal measurement. The method further includes, responsive to the performing, detecting a plurality of objects in an area proximate the communication device; and generating information about the detected plurality of objects. The method further includes extracting, from the generated information, the environmental information including an environmental description information and a position description information for the plurality of objects relative to the communication device.

Abstract: A device may identify tasks relevant to closing processes for an entity during a period of time, and may generate a request for historical closing data associated with the tasks relevant to the closing processes. The device may provide the request to a server device associated with the entity, and may receive the historical closing data based on providing the request. The device may train a machine learning model, based on the historical closing data, to generate a trained machine learning model, and may receive current closing data associated with tasks relevant to a current closing process. The device may process the current closing data, with the trained machine learning model, to predict issue data identifying at least one potential issue associated with the current closing process, and may provide the issue data to a user device associated with the at least one potential issue.

Abstract: A computer implemented method is provided for training a policy for managing an environment in a communication network. The method includes selecting an action which will maximise a future predicted value of a reward function, given a current belief state of the environment, and recording an explanation tree for the selected action. The explanation tree includes a representation of the current belief state, available actions, and predicted reward function values associated with the available actions. The method further includes causing the selected action to be executed and obtaining an observation following execution of the selected action. The method further includes using a second policy function to generate an updated current belief state based on the obtained observation, and on a probability that an explanation for the selected action would be accepted by an entity querying the selected action, the explanation being generated using the explanation tree.

Abstract: A method of performing multi-agent reinforcement learning in a system including a master node and a plurality of agents that execute actions on an environment based on respective local policies of the agents is provided. The method includes generating a ranking of the plurality of agents based on levels of variability of stochastic processes underlying the behavior of respective ones of the plurality of agents, sequentially updating the local policies of the agents in order based on the ranking, wherein the local policy of a selected agent is updated conditioned on an expected next state of at least one previously selected agent, simultaneously executing actions by agents based on their updated local policies, and updating the ranking of the plurality of agents in response to executing the actions.

Abstract: A method performed by a node for predicting a behavior of users of a communications network is described. The node manages an artificial neural network. The node merges a first pre-existing predictive model of the behavior in a first group of users with a second model of the behavior in a second group of users. The merging comprises establishing connections between the first model and the second model. Each of the connections has a respective weight. The respective weights of the connections are learned by respective connections of neurons in the artificial neural network based on data from a third group of users. The node also obtains a third model for predicting the behavior in the third group of users, based on the merged models and the data from the third group of users.

Abstract: A computer-implemented method includes: obtaining loss functions including: a first loss function associated with a first reinforcement learning, RL, model performed by a first local agent, wherein the first loss function is a function of one or more first parameters; and a second loss function associated with a second RL model at a second local agent, wherein the second loss function is a function of one or more second parameters; determining a combined loss function based on the loss functions; minimizing the combined loss function with respect to the first parameters and the second parameters to determine updated values for the first parameters and updated values for the second parameters; initiating execution of a first updated action by the first local agent based on the updated values of the first parameters; and initiating execution of a second updated action by the second local agent based on the updated values of the second parameters.

Abstract: It is provided a method for adjusting alignment for microwave transmissions from a microwave transmitter to a microwave receiver based on a reinforcement learning, RL, model. The method comprises the steps of: obtaining state space comprising external state space and internal state space, the external state space comprising at least one value of a parameter related to environmental conditions, and the internal state space relates to alignment of the microwave transmitter; determining an action in an action space, the action space comprising actions to adjust alignment of the microwave transmitter; obtaining a measurement of path loss for a transmission from the microwave transmitter to the microwave receiver; determining a reward value based on the path loss, wherein an increase in path loss results in a reduced reward value; and adjusting the RL model based on the obtained state space, the determined action and the determined reward value.

Abstract: The present disclosure relates to a method of a wireless communication device (103) of facilitating control of antenna tilt for a radio base station (101), a method of a radio base station (101) of facilitating control of antenna tilt at the radio base station (101) and further a wireless communication device (103) and a radio base station (101) performing the respective method. In a first aspect a method of a wireless communication device (103) of facilitating control of antenna tilt for a radio base station (101) is provided.

Abstract: Managing network event data in a telecommunication network. The method includes obtaining a plurality of datasets having network event data associated with products provided by a different vendor, the network event data comprising a plurality of data instances representing a plurality of network event features. The method further comprises obtaining metadata describing the network event data in the datasets and generating feature description vectors from the obtained metadata, calculating a metric of the relation between network event features represented in the datasets and constructing a graph of the network event features represented in the datasets, with edges weighted according to the calculated metric, partitioning the graph into clusters by minimising an edge cut between network event features, labelling network event features in the cluster with a normalised network event feature index and inputting the labelled network event data to a model for making at least one of recommendations or predictions.

Abstract: A method is herein provided, performed by a network node for handling configuration of radio network nodes in a wireless communication network. The network node such as a O&M node or similar calculates a configuration for one or more radio network nodes by using a machine learning model with a search space of parameters, wherein the search space is reduced based on an importance factor for parameters of the radio network nodes and/or the wireless communication network.

Abstract: A method performed by a content server (100) for determining additional media content to be inserted into a main media content wherein the main media content is in a virtual environment, the method comprising: acquiring (S201) information relating to a user profile of each of a plurality of users that are viewing the main media content; clustering (S202) the plurality of users into one or more user clusters based on the user profile of each of the plurality of users; acquiring (S203) a viewing state of each of the plurality of users that are viewing the main media content, wherein the viewing state of each of the plurality of users comprises biometric data of each of the plurality of users; acquiring (S204) information relating to a network quality; and determining (205) the additional media content for each of the plurality of users by a first reinforcement learning agent based on the one or more user clusters, the viewing state of each of the plurality of users, and the network quality.

Abstract: (57) Abstract: A method, performed by a first node (111), for handling parameters to configure a second node (112). The first node (111) determines (207) parameters to configure the second node (112). The determining (207) is based on an analysis by a Generative Adversarial Network comprising performing iteratively: i) generating a set of parameters estimated to be linked to a performance of a first group of nodes (121) being above a threshold, and ii) discriminating between the generated set of parameters and a first set of parameters observed to be linked to the performance of the first group of nodes (121) being above the threshold to obtain a score for every parameter. The score indicates how different the generated parameters and the first set of parameters are. The determined parameters have the score resulting from the discriminating being lower than anotherthreshold. The first node (111) also outputs an indication comprising the determined parameters.

Abstract: Managing network event data in a telecommunication network. The method includes obtaining a plurality of datasets having network event data associated with products provided by a different vendor, the network event data comprising a plurality of data instances representing a plurality of network event features. The method further comprises obtaining metadata describing the network event data in the datasets and generating feature description vectors from the obtained metadata, calculating a metric of the relation between network event features represented in the datasets and constructing a graph of the network event features represented in the datasets, with edges weighted according to the calculated metric, partitioning the graph into clusters by minimising an edge cut between network event features , labelling network event features in the cluster with a normalised network event feature index and inputting the labelled network event data to a model for making at least one of recommendations or predictions.

Abstract: It is provided a method for adjusting alignment for microwave transmissions from a microwave transmitter to a microwave receiver based on a reinforcement learning, RL, model. The method comprises the steps of: obtaining state space comprising external state space and internal state space, the external state space comprising at least one value of a parameter related to environmental conditions, and the internal state space relates to alignment of the microwave transmitter; determining an action in an action space, the action space comprising actions to adjust alignment of the microwave transmitter; obtaining a measurement of path loss for a transmission from the microwave transmitter to the microwave receiver; determining a reward value based on the path loss, wherein an increase in path loss results in a reduced reward value; and adjusting the RL model based on the obtained state space, the determined action and the determined reward value.

Abstract: A device may identify tasks relevant to closing processes for an entity during a period of time, and may generate a request for historical closing data associated with the tasks relevant to the closing processes. The device may provide the request to a server device associated with the entity, and may receive the historical closing data based on providing the request. The device may train a machine learning model, based on the historical closing data, to generate a trained machine learning model, and may receive current closing data associated with tasks relevant to a current closing process. The device may process the current closing data, with the trained machine learning model, to predict issue data identifying at least one potential issue associated with the current closing process, and may provide the issue data to a user device associated with the at least one potential issue.

Abstract: The disclosure provides methods, apparatus and machine-readable mediums for mitigating power failures in base stations in wireless communication networks. In one aspect of the disclosure, a method for mitigating power failures in a wireless communication network is provided. The method comprises, responsive to a determination that a primary power supply for a base station in the wireless communication network has failed or is predicted to fail, initiating deployment of an unmanned aerial vehicle to the base station to charge one or more batteries providing a secondary power supply for the base station.