Abstract: A machine-learning (ML) orchestrator entity provides distributed, flexible, and efficient parameter initialization and updating for ML agents can be installed on network nodes operating under similar radio conditions. The ML orchestrator entity instructs each of such network nodes to iteratively run the ML agent in a training mode. Each run yields a local set of parameters for the ML agent. After each run, the ML orchestrator entity collects and uses the local sets of parameters from two or more network nodes to derive a common set of parameters for the network nodes. The ML orchestrator further instructs each of the network nodes to update its own local set of parameters based on the common set of parameters and use the updated local set of parameters in a subsequent run. The ML orchestrator entity repeats these steps until a termination criterion for the training mode is met.

Abstract: An apparatus comprising: means for receiving configuration from a first node, the configuration relating to collection of training data during a handover of the apparatus from the first node to a second node; means for controlling collection of training data from measurements during the handover based on the configuration; means for informing the second node a state of the collection of the training data from the measurements following a completion of the handover; and means for transferring any collection of the training data from the measurements to the second node following the completion of the handover.

Abstract: A method is provided that includes receiving system information at a user equipment (UE) operable in a network that serves a plurality of UEs. The UE is implemented as a specific-purpose that supports one or more specific-purpose features of the network, and the system information includes a list of network signaling (NS) values associated with respective emission requirements for radio frequency (RF) transmission by the plurality of UEs. The method includes selecting a specific-purpose NS value at the specific-purpose UE, with the specific-purpose NS value associated with an emission requirement for RF transmission by the specific-purpose UE. And the method includes applying the emission requirement for RF transmission by the specific-purpose UE. An associated apparatus that may be implemented as the special-purpose UE is also provided.

Abstract: Example embodiments of the present disclosure relate to methods, devices, apparatuses and computer readable storage medium for capability information transmission. In a method, a first apparatus receives, from a second apparatus, a capability enquiry comprising Machine Learning (ML) capabilities with one or more applicable conditions and an indication requesting the first apparatus to indicate support of at least one activation condition for the applicable conditions. The first apparatus transmits, to the second apparatus, capability information comprising the applicable conditions and the at least one activation condition for the applicable conditions. The at least one activation condition indicates whether a corresponding applicable condition is currently supported or not supported.

Abstract: Triggering of artificial intelligence/machine learning training in a network data analytics function is provided. A method for triggering artificial intelligence/machine learning training in a network data analytics function may include obtaining at least one machine learning model for training or retraining based on measurement data of a network. The method may also include determining that data collection is required prior to training or retraining the at least one machine learning model, and receiving one or more measurement reports that includes at least one dataset from the data collection. The method may further include determining whether additional assisted information from one or more network devices is required for training or retraining. The at least one machine learning model may be trained or retrained based on all collected datasets, which includes the at least one dataset from the data collection.

Abstract: The present disclosure relates to a machine-learning (ML) orchestrator entity that provides distributed, flexible, and efficient parameter initialization for ML agents installed on network nodes operating under similar radio conditions. For this end, the ML orchestrator entity instructs two or more of the network nodes to run two or more ML agents in a training mode, which results in generating two or more sets of parameters. Then, the ML orchestrator entity uses the sets of parameters to derive a common set of parameters for the network nodes. The common set of parameters is to be used in an inference mode of the ML agent at each of the network nodes. The transmission of the common set of parameters to the network nodes may be subsequently initiated by the ML orchestrator entity itself or by each of the network nodes independently.

Abstract: A method including receiving a configuration indicating one or more rules for switching between a set of operational modes associated with at least one of: inference, data collection or training of a machine learning model, the machine learning model being associated with a network optimization function; determining, based on the one or more rules, whether to switch from a current operational mode to another operational mode from the set of operational modes; and performing the current operational mode or the other operational mode based on the determination.

Abstract: Various example embodiments relate to a solution for modifying mobility events by making them depend on information which captures a moving cell direction. A network node may obtain coverage information associated with a serving network and a target network. The network node may obtain synchronization signal timing data associated with the target network. The network node may determine time drift rate data for at least one user node based at least partly on location data and satellite ephemeris data. The network node may cause transmission of the time drift rate data associated with the time drift to the at least one user node to enable the user node to perform a measurement of a target cell of the target network using the time drift rate data. Nodes, methods, and computer programs are disclosed.

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: An apparatus, method and computer program is described comprising: determining, at a user device of a mobile communication system, one or more parameters of a serving cell and one or more target cells at a first time instance; and estimating one or more time delay metrics for each of the one or more target cells based on said parameters, such that an optimal time point for performing a handover can be determined. The time delay metrics comprise one or more of: a first time delay corresponding to a time period between the first time instance and a time instance at which a signal strength of the serving cell is predicted to match a signal strength of the respective target cell; and a second time delay corresponding to a time period between the first time instance and a time instance at which the signal strength of the respective target cell is predicted to be higher than the signal strength of the serving cell by an offset value.

Abstract: A method, apparatus and computer program product are provided for cell change assistance in a non-terrestrial network. NTN, with a plurality of moving cells served by at least one satellite. A network element of the NTN provides cell change assistance information to a user equipment, UE, for selecting at least one moving cell of the plurality of moving cells. The UE receives cell change assistance information for selecting a cell for cell change. The cell change assistance information identifies at least a subset of the plurality of moving cells and us indicative of a geometric layout of at least the subset of the plurality of moving cells.

Abstract: An apparatus configured to: enter a test mode; receive, from a test equipment, an indication of at least one first model used at a first side of a two-sided model; request, from a model repository, at least one second model for use at a second side of the two-sided model, wherein the at least one second model is selected based, at least partially, on the at least one first model; and receive, from the model repository, the at least one second model. An apparatus configured to: receive, from a test equipment, a model validation request; provide a data set to at least one model to obtain an inference validation response, wherein the at least one model is used at a first side of a two-sided model; transmit, to the test equipment, the inference validation response; and receive, from the test equipment, a validation sequence result.

Abstract: There is provided an apparatus comprising means for communicating a travel path plan of the apparatus to a communication network; means for receiving from the communication network information of one or more cells of the communication network associated with priorities of accessing; and means for using the received information for adjusting priorities for measurements towards different cells of the network. There is also provided a method and a computer program product.

Abstract: Embodiments of the present disclosure relate to conditional handover. A method comprises: upon a successful handover to a first target cell in an ordered list of target cells configured for a terminal device to initiate handover in order, determining, at the terminal device, information for assessing a validity of the ordered list; and transmitting, to a first network device providing the first target cell, a first message comprising the information for assessing the validity of the ordered list. In this way, a chain of target cells is capable of preparing for the future handover from the suitable time, which avoids reserving resources too early or too late and improves the resource efficiency. Moreover, the current serving cell can detect the deviation of the terminal device from the chain in time, thus a configuration of the ordered list can be appropriately adjusted or updated.

Abstract: According to an aspect, there is provided an apparatus for performing the following. The apparatus performs cell-specific radio measurements for a plurality of cells or beam-specific radio measurements for a plurality of transmit beams. The apparatus evaluates correlation between results of the cell/beam-specific radio measurements and compares the correlation against one or more pre-defined correlation conditions. In response to the correlation for at least one pair of cells in the plurality of cells or for at least one pair of transmit beams in the plurality of transmit beams satisfying the one or more pre-defined correlation conditions, the apparatus filters the results of the cell-specific or beam-specific radio measurements to remove repetitions of results satisfying the one or more pre-defined correlation conditions and transmits, to another apparatus, a measurement report comprising the filtered results and information on the correlation.

Abstract: In accordance with example embodiments of the invention there is at least a method an apparatus to perform receiving or sending, between a network node of a communication network, and a user equipment information comprising a service request for a dedicated bearer for data exchange of at least one of machine learning or artificial intelligence related data, wherein the data exchange is for training at least one of a machine learning or an artificial intelligence model for a particular use case; communicating the information with the communication network; handling control over at least one of an artificial intelligence or machine learning related data exchange through a machine learning-dedicated bearer, wherein the artificial intelligence or machine learning related data exchange comprises: data collection, model transfer, and life cycle Management for at least one of a machine learning model or machine learning functionality control signalling.

Abstract: According to an example embodiment, a network node device is configured to generate at least one client cluster comprising at least one client device served by the network node device according to at least one clustering criterion; assign the at least one control algorithm instance to the at least one client cluster; control at least one transmission power control parameter of the at least one client device in the at least one client cluster using the at least one control algorithm instance.

Abstract: A method includes receiving, by a first user device from a network node, an indication for the first user device to act as a user device-network relay; and, in response to the receiving: carrying out a discovery procedure for determining at least one second user device that is capable of sidelink communications and utilizes machine learning; receiving, by the first user device from the network node, machine learning configuration information; and transmitting, by the first user device to the at least one second user device via sidelink communications, the machine learning configuration information for carrying out a machine learning related operation.

Abstract: There are provided measures for enabling/realizing efficient model training, including model collection and/or aggregation, for federated learning, including hierarchical federated learning, in a wireless communication system. Such measures exemplarily comprise that a federated-learning training host configured for local model training decides on how to perform the local model training depending on availability of a cluster head and computation and communication costs for a federated-learning training task, and either locally performs the local model training or delegates at least part of a federated-learning training task to the cluster head. Also, such measures exemplarily comprise that a federated-learning training host configured for local model training computes a similarity metric between a locally computed set of local model parameters and each the received sets of local model parameters, and decides on whether to operate as a temporary cluster head for one or more federated-learning training hosts.

Abstract: Systems, methods, apparatuses, and computer program products for testing user equipment (UE) machine learning-assisted radio resource management (RRM) functionalities are provided. One method may include selecting a radio resource management (RRM) functionality to be tested for a user equipment (UE) having advertised machine learning (ML)-assistance capabilities, initializing a machine learning (ML)-assistance model in the user equipment based on the advertised machine learning (ML)-assistance capabilities, generating one or more input test signals and corresponding reference output test conditions depending on the machine learning (ML)-assistance radio resource management (RRM) functionality under test, and activating UE machine learning (ML)-assistance functionality and provisioning, to the user equipment, a test sequence with the generated input test signals and corresponding reference output conditions.