Abstract: According to an example embodiment, a network node device is configured to obtain measurement data of radio measurements from at least one client device; detect an outage and/or failure of the at least one client device during a first prediction period; based on the measurement data and the detected outage and/or the detected failure, train a prediction model to predict an outage and/or failure probability during a prediction period from measurement data of radio measurements; and provide the trained prediction model to the at least one client device.

Abstract: Disclosed is a method comprising obtaining a reliability estimate indicating transmission success probability for a plurality of transmission legs and assigning a data packet type to a subset of the plurality of transmission legs based at least partly on said reliability estimate.

Abstract: Techniques of updating ML models include performing such an update when the UE satisfies certain criteria. In some implementations, the ML model is used by the UE to determine a location within a network. In some implementations, the criteria include a version number of the ML model being used by the UE. In some implementations, the criteria include a time elapsed since a last ML model update was provided to the user equipment.

Abstract: A method for optimizing a predictive model for a group of nodes in a communications network includes receiving a tuples of data values, each tuple including state data representative of a state of a node, an action including a specification of paths for duplicating data packets from the node to a further node, and reward data that indicates a quality of service at the node subsequent to duplicating data packets through the paths specified by the action, determining a data value indicative of a performance level for the communications network on the basis of reward data of the tuples, evaluating a predictive model that outputs a set of data values for each node, the data values predicting a quality of service from duplicating data packets on the paths, and modifying the predictive model based on the predicted data values and the data value indicative of a performance level for the communications network.

Abstract: Disclosed are two methods, the first method comprising receiving a plurality of data packets, producing a coded data packet by coding together at least two data packets, wherein at least one of the at least two data packets is comprised in the received plurality of data packets or in a coding buffer, transmitting the at least two data packets to a first subset of legs, transmitting the coded data packets to a second subset of legs, and determining if the at least two data packets are to be duplicated based on, at least partly, one or more of the following: a notification, a condition, or a first indication.

Abstract: According to an example embodiment, a client device is configured to receive a validation model from a centralised unit device, wherein the validation model includes a machine learning model configured to predict an output from an input based on a plurality of model parameters; collect radio measurements corresponding to the input of the validation model and parameters corresponding to the output of the validation model; obtain predicted parameters as the output of the validation model by feeding the collected radio measurements as the input into the validation model; compare the collected parameters and the predicted parameters; compute a plurality of gradient vectors for the plurality of model parameters of the validation model based on the comparison between the collected parameters and the predicted parameters; and transmit the plurality of gradient vectors for the plurality of model parameters of the validation model to the centralised unit device.

Abstract: Disclosed are two methods, the first method comprising receiving a plurality of data packets, producing a coded data packet by coding together at least two data packets, wherein at least one of the at least two data packets is comprised in the received plurality of data packets or in a coding buffer, transmitting the at least two data packets to a first subset of legs, transmitting the coded data packets to a second subset of legs, and determining if the at least two data packets are to be duplicated based on, at least partly, one or more of the following: a notification, a condition, or a first indication.

Abstract: Disclosed is a method comprising obtaining a reliability estimate indicating transmission success probability for a plurality of transmission legs and assigning a data packet type to a subset of the plurality of transmission legs based at least partly on said reliability estimate.

Abstract: Systems, methods, apparatuses, and computer program products for real-time uplink (UL) power control are provided. One method may include estimating, by a network node, a power allocation function for determining power allocation across a plurality of legs that transmit simultaneously, the power allocation function being based on radio channel statistics and network performance metrics. The method may then include signaling, to a user equipment, the power allocation function and the parameters used to compute an output of the power allocation function.

Abstract: Systems, methods, apparatuses, and computer program products for real-time uplink (UL) power control are provided. One method may include estimating, by a network node, a power allocation function for determining power allocation across a plurality of legs that transmit simultaneously, the power allocation function being based on radio channel statistics and network performance metrics. The method may then include signaling, to a user equipment, the power allocation function and the parameters used to compute an output of the power allocation function.

Abstract: The present disclosure describes example communication methods, terminals, access network devices, and core network devices. One example communication method includes sending, by an access network device, a slice resource adjustment message to a terminal, where the slice resource adjustment message includes target resource information, and wherein the slice resource adjustment message is used to instruct the terminal to adjust a resource of a slice currently accessed by the terminal to the target resource. The access network device receives a slice resource adjustment complete message sent by the terminal, where the slice resource adjustment complete message is used to indicate that the terminal has adjusted the resource of the slice currently accessed by the terminal to the target resource.

Abstract: The present disclosure describes example communication methods, terminals, access network devices, and core network devices. One example communication method includes sending, by an access network device, a slice resource adjustment message to a terminal, where the slice resource adjustment message includes target resource information, and wherein the slice resource adjustment message is used to instruct the terminal to adjust a resource of a slice currently accessed by the terminal to the target resource. The access network device receives a slice resource adjustment complete message sent by the terminal, where the slice resource adjustment complete message is used to indicate that the terminal has adjusted the resource of the slice currently accessed by the terminal to the target resource.