Abstract: A computer-implemented method is provided performed by a client computing device for decentralized learning based on local learning at the client computing device is provided. The method includes training a local M, model based on an activation function using a local parameter set and a reference parameter set to obtain a setting for respective 5 local parameters in the local parameter set that minimizes a training loss wherein the activation function preserves agreements and discourages disagreements between the local parameter set and the reference parameter set. The method further includes sending the trained local ML model to a server computing device. The method further includes receiving, from the server computing device, a global ML model that meets a convergence criterion. A 10 method performed by a server computing device, and related methods and apparatuses are also provided.

Abstract: There is provided a method comprising: acquiring (110) sensor data related to an object; using the first learning module, identifying (120) the object based on the acquired sensor data using a first learning module and determining (130) a user associated with the identified object; determining (140) a timestamped location of the object based on at least one of the acquired sensor data and one or more locations of the one or more sensors; performing (150) a first analysis to determine whether the current status of the object contains an anomaly based on one or more predefined rules stored in a knowledge base; performing (160) a second analysis to determine whether the current status of the object contains an anomaly, using a second learning module; and validating (170) whether the current status of the object contains an anomaly based on results of the first analysis and results of the second analysis.

Abstract: A computer-implemented method and apparatus for feature selection using a distributed machine learning (ML) model in a network comprising a plurality of local computing devices and a central computing device is provided. The method includes training, at each local computing device, the ML model during one or more initial training rounds using a group of input features representing a input features layer of the ML model. The method further includes generating, at each local computing device, based on the one or more initial training rounds, feature group values. The method further includes transmitting, from each local computing device, to the central computing device, the generated feature group values. The method further includes receiving, at each local computing device, from the central computing device, central computing device gradients. The method further includes computing, at each local computing device, local computing device gradients, using the received central computing device gradients.

Abstract: A method, system and apparatus are disclosed. A method implemented in a source network node configured to communicate with a target network node is provided. A source data set is obtained. A source model is trained based on the source dataset, where the training includes generating a source memory matrix and a source link matrix. The source memory matrix and the source link matrix are transmitted to the target network node, which causes the target network node to train a target model. The training of the target model includes initializing a target memory matrix and a target link matrix based on the source memory matrix and the source link matrix.

Abstract: A system (200), a first network node (240), a method, a computer program and a computer program product for training of a Federated Learning. FL, model is disclosed. The system comprises network nodes. One of the network nodes is a first network node. Each network node has access to a part of the network data. The system obtains network information and determines groups of network nodes and assigns each network node to one of the determined groups based on the network information, each determined group of network nodes comprising at least two network nodes. For each of the groups, the system appoints a second network node from among the at least two network nodes, informs the at least two network nodes about the appointed second network node and trains an FL model using the parts of the network data accessible by the at least two network nodes.

Abstract: A method of detecting a defect in a connecting member of a radio unit in a radio site includes applying an artificial radio traffic load to a first radio unit and at least a second radio unit, such that the radio traffic load experienced by the first and the second radio unit is at a same level, measuring power supplied to the first radio unit via a first connecting member and power supplied to the second radio unit via a second connecting member at an end of each connecting member terminating at a device configured to supply power to the radio units, and determining from the measured power and an expected nominal power loss of the first and the second connecting member if there is power loss in at least one of the first and the second connecting member indicating a defect.

Abstract: A method of detecting a defect in a connecting member of a radio unit in a radio site includes applying an artificial radio traffic load to a first radio unit and at least a second radio unit, such that the radio traffic load experienced by the first and the second radio unit is at a same level, measuring power supplied to the first radio unit via a first connecting member and power supplied to the second radio unit via a second connecting member at an end of each connecting member terminating at a device configured to supply power to the radio units, and determining from the measured power and an expected nominal power loss of the first and the second connecting member if there is power loss in at least one of the first and the second connecting member indicating a defect.

Abstract: Methods and systems for source machine learning (ML) model selection for the transfer learning. A method may include receiving a source ML model request from a target domain, determining candidate source ML models, calculating a model quality score for each of the candidate source ML models, using the calculated model quality scores to select candidate source ML models, sending the selected candidate source ML models to the target domain, receiving fine-tuned ML model weights for fine-tuned ML models, and calculating a model quality score for each of the fine-tuned ML models. The method may include determining, for each of the fine-tuned ML models, a ranking and/or a deployment recommendation for the fine-tuned ML model based on the model quality score for the fine-tuned ML model and sending, for each of the fine-tuned ML models, the ranking and/or the deployment recommendation for the fine-tuned ML model to the target domain.

Abstract: The present disclosure relates to a method of controlling allocation of mobile devices (12-23) to frequency bands in a radio site (10), and a device (11) performing the method. In an aspect, a method of a radio base station (11) of controlling allocation of mobile devices (12-23) to frequency bands in a radio site (10) is provided. The method comprises estimating (S101) power consumption of the radio base station (11) caused by radio traffic of the mobile devices (12-23) in each frequency band of the radio site (10), determining (S102) whether or not power consumption of the radio base station (11) is decreased by reallocating at least one of the mobile devices (12-23) from one frequency band to another frequency band, while not exceeding a power headroom limit of said another frequency band, and if so reallocating (S103) said at least one mobile device from said one frequency band to said another frequency band.

Abstract: There is provided a method comprising: acquiring (110) sensor data related to an object; using the first learning module, identifying (120) the object based on the acquired sensor data using a first learning module and determining (130) a user associated with the identified object; determining (140) a timestamped location of the object based on at least one of the acquired sensor data and one or more locations of the one or more sensors; performing (150) a first analysis to determine whether the current status of the object contains an anomaly based on one or more predefined rules stored in a knowledge base; performing (160) a second analysis to determine whether the current status of the object contains an anomaly, using a second learning module; and validating (170) whether the current status of the object contains an anomaly based on results of the first analysis and results of the second analysis.

Abstract: The present disclosure relates to methods and devices (101, 106) of controlling reactive power of a power grid. In an aspect, a method of a radio base station (101) of controlling reactive power of a power grid is provided. The method comprises measuring (S101) an electrical property indicating a level of the reactive power supplied by the power grid to which the radio base station (101) is connected, and performing (S102) an action to stabilize the level of the reactive power of the power grid upon the measured electrical property reaching a certain value.

Abstract: The present disclosure relates to a method of controlling allocation of mobile devices (12-23) to frequency bands in a radio site (10), and a device (11) performing the method. In an aspect, a method of a radio base station (11) of controlling allocation of mobile devices (12-23) to frequency bands in a radio site (10) is provided. The method comprises estimating (S101) power consumption of the radio base station (11) caused by radio traffic of the mobile devices (12-23) in each frequency band of the radio site (10), determining (S102) whether or not power consumption of the radio base station (11) is decreased by reallocating at least one of the mobile devices (12-23) from one frequency band to another frequency band, while not exceeding a power headroom limit of said another frequency band, and if so reallocating (S103) said at least one mobile device from said one frequency band to said another frequency band.

Abstract: A method for solving a sequential decision-making problem is provided. The method includes gathering state-action pair data from an expert policy; applying imitation learning to yield a cloned policy based on the gathered state-action pair data from the expert policy; and applying a reinforcement learning technique, wherein the reinforcement learning technique is initialized based on the cloned policy and has an output with one or more action to be performed for solving the sequential decision-making problem.

Abstract: Embodiments herein disclose, e.g., a method performed by a control network node in a communications network for handling machine learning (ML) models in the communications network. The control network node determines whether or not to transmit to a network node in the communications network a ML model based on a signature and/or a loss value of the network node, wherein the signature and/or the loss value is related to ML modelling. In case where it is determined to transmit, the control network node transmits the ML model to the network node.

Abstract: A method of detecting a defect in a connecting member of a radio unit in a radio site includes applying an artificial radio traffic load to a first radio unit and at least a second radio unit, such that the radio traffic load experienced by the first and the second radio unit is at a same level, measuring power supplied to the first radio unit via a first connecting member and power supplied to the second radio unit via a second connecting member at an end of each connecting member terminating at a device configured to supply power to the radio units, and determining from the measured power and an expected nominal power loss of the first and the second connecting member if there is power loss in at least one of the first and the second connecting member indicating a defect.

Abstract: A method and detector for detecting anomalies among media event sequences are disclosed. One method includes obtaining a first profile of media event data over a first time period, where the first profile is a first distribution of different media event sequences. Each sequence is associated with a number of occurrences of the sequence and the first profile having a first profile vector. The method further includes obtaining a second profile of media event data over a second time period less than the first time period. The second profile is a second distribution of the different media sequences and the second profile having a second profile vector. The method also includes comparing the first profile vector and the second profile vector, and determining one of a presence and absence of at least one anomaly in the second profile vector of media event data based on the comparison.

Abstract: A method and a communication device (200) for controlling reception of data when a maximum total amount of received data is stipulated for a time period. An amount of data received during said time period is monitored (2:5) and compared with a predicted distribution of data (200A) that the device (200) is expected to receive without exceeding the maximum total amount. An amount of requested data is then reduced (2:6, 2:7) when detecting that the monitored amount of received data exceeds the predicted distribution of data, so that the maximum total amount of data will not be exceeded before the time period expires.

Abstract: A method and a migration managing module for managing a migration of a service. The migration managing module determines a point in time relating to completion of the migration of the service based on resource requirements related to the service. For each radio network node a respective impact on a quality of the service is estimated. Moreover, the migration managing module selects from among servers at least one respective target server for which the respective server location measure of said at least one respective target server matches the respective radio network node location measure of said each radio network node, thereby obtaining a set of target servers comprising said at least one respective target server for said each radio network node. For each target server, a respective cost of the migration based on the resource requirements related to the service is determined. A respective tendency as a function of said each probability value, the respective cost and the respective impact is determined.

Abstract: A method and detector for detecting anomalies among media event sequences are disclosed. One method includes obtaining a first profile of media event data over a first time period, where the first profile is a first distribution of different media event sequences. Each sequence is associated with a number of occurrences of the sequence and the first profile having a first profile vector. The method further includes obtaining a second profile of media event data over a second time period less than the first time period. The second profile is a second distribution of the different media sequences and the second profile having a second profile vector. The method also includes comparing the first profile vector and the second profile vector, and determining one of a presence and absence of at least one anomaly in the second profile vector of media event data based on the comparison.

Abstract: A method and a migration managing module for managing a migration of a service. The migration managing module determines a point in time relating to completion of the migration of the service based on resource requirements related to the service. For each radio network node a respective impact on a quality of the service is estimated. Moreover, the migration managing module selects from among servers at least one respective target server for which the respective server location measure of said at least one respective target server matches the respective radio network node location measure of said each radio network node, thereby obtaining a set of target servers comprising said at least one respective target server for said each radio network node. For each target server, a respective cost of the migration based on the resource requirements related to the service is determined. A respective tendency as a function of said each probability value, the respective cost and the respective impact is determined.