Abstract: A content distribution node that distributes content to display devices which are arranged in a spaced apart sequence along a pathway of vehicles for display to passengers. The content distribution node receives from a mobile gateway node of a vehicle, through a Light Fidelity signal receiver circuit, a profile message containing profile information related to the vehicle. The content distribution node selects, from among content files available in a content repository, a set of video frames for distribution to the display devices based on the profile information. The content distribution node distributes different video frames among the set of video frames to different ones of the display devices with timing of the distribution that allows the video frames among the set to be displayed on respective ones of the display devices in the sequence before arrival of the vehicle within a field-of-view of at least one of the display devices.

Abstract: A method of performing federated feature selection for a machine learning model in a federated learning environment includes obtaining, at a first resolution, a global set of selector neural network weights. At a second resolution, the method selects, for a plurality of first data subsets, a first set of features from a feature space by iteratively applying a first selector neural network that is initialized with the global set of selector neural network weights to the first data subset to obtain a first set of selector neural network weights. The first data subsets are divided into a plurality of second data subsets, and, at a third resolution, a second set of features is selected from the feature space.

Abstract: Methods and devices optimize backup power management for network devices connected to backup power sources including two different batteries. Machine learning techniques are used to predict upcoming power outages affecting the network device based on power-related historic information and current conditions. A backup-power operation plan prescribing usage of the backup power sources during the predicted power outages is then generated. The backup-power operation plan schedules a battery among the backup power devices to be used at least twice without being recharged.

Abstract: Embodiments described herein provided methods and apparatus for executing a machine-learning model. A first machine-learning model, based on a first set of data and using a machine-learning algorithm, is developed at a first node. A second machine-learning model, based on the first machine-learning model and a second set of data, and using the machine-learning algorithm, is developed at a second node. Information about a difference between the first machine-learning algorithm, at a second node machine-learning model and the second machine-learning model is communicated from the second node to the first node. A request for execution of a machine-learning model is received at the first node. Responsive to receiving the request for the execution of the machine-learning model, information indicative of an execution policy is obtained at the first node.

Abstract: A method of operating a protection node for protecting a pattern classification node from malicious requests may be provided. The protection node may receive, from a user node, a request containing an original pattern to be classified by a machine learning algorithm performed by the pattern classification node. The protection node may add noise to the original pattern to generate a noisy pattern. The protection node may obtain a first classification of the noisy pattern based on processing of the noisy pattern by a first clone of the machine learning algorithm at the protection node; obtain a second classification of the original pattern based forwarding the request for processing of the original pattern by the machine learning algorithm performed at the pattern classification node; and compare the first and second classifications to determine whether the first and second classifications satisfy a defined similarity rule. The protection node may use the comparison to manage the request from the user node.

Abstract: A regulator system (24) of a regulator regulates administration of subscription identifiers. The regulator system (24) is configured to receive, from either an operator system (10) of a wireless communication network operator or an enterprise system of an enterprise, a record that includes information about administration of a subscription identifier associated with the wireless communication network operator. The regulator system (24) is also configured to verify whether administration of the subscription identifier as indicated by the record conforms to one or more rules (34) governing administration of subscription identifiers. The regulator system (24) is further configured to, depending on the verification, approve or reject the record for addition to a permissioned distributed database (26) (e.g., a permissioned blockchain) that is distributed at least in part between the regulator system (24) and either the operator system (10) or the enterprise system.

Abstract: Methods and devices optimize backup power management for network devices connected to backup power sources including two different batteries. Machine learning techniques are used to predict upcoming power outages affecting the network device based on power-related historic information and current conditions. A backup-power operation plan prescribing usage of the backup power sources during the predicted power outages is then generated. The backup-power operation plan schedules a battery among the backup power devices to be used at least twice without being recharged.

Abstract: A method performed by a network node for handling one or more upcoming requests for one or more services from a communication device in a communications network using a cloud infrastructure is provided. The network node obtains (301) a prediction of an amount of instances needed for the one or more upcoming requests for the one or more services, based on historical data of previous requests for services, and obtains (304) network connections needed for the one or more upcoming requests for the one or more services, taking the prediction into account. Furthermore, the network node decides (307) to instantiate a service with the obtained network connections and/or the amount of instances as predicted.

Abstract: A method in a control unit for configuration in a wireless communication system is provided. A service category is mapped to a virtual network instance based on service requirements of the service category, the virtual network instance having a first virtual network instance configuration for a current time interval, the first virtual network instance configuration defining a first allocation of resources in a plurality of network layers. A network state in a next time interval is predicted and it is determined if the predicted network state results in a predicted performance degradation in the next time interval. On condition that there is a predicted performance degradation, a second virtual network instance configuration is determined for the next time interval. The virtual network instance is configured based on the first network instance configuration or the second network instance configuration.

Abstract: There is provided a system and a method for controlling a vehicle. A path is determined, to be followed by the vehicle between a starting location and an intended destination location. The vehicle is controlled to follow the determined path. An indication may be received from the vehicle of the presence of a potential difficulty in respect of the determined path. The method determines the source of any potential difficulty and interacts with the source thereby to re-configure at least one of the source and the vehicle to enable onward progress of the vehicle along the determined or an updated path. The system comprises a controller and a vehicle interface. The controller implements the method and interacts with the vehicle via the vehicle interface. The method and the system may control the vehicle to conduct a field service operation in respect of a network node of a wireless communications network.

Abstract: Embodiments herein relate, in some examples, to an intermediate network node configured to operate in a communication network. The communication network comprises a requesting node and an executing network node comprising a computational graph model. The intermediate network node is configured with an imitation model. The imitation model is a limited version of the computational graph model, and the imitation model is a model requiring less computational resources to converge when compared to the computational graph model.

Abstract: Method and system for Root Cause Analysis (RCA) across multiple network systems. Update information of a first local root cause analysis mechanism is received. An RCA controller generates, based on the update information, a new node to be added to a global root cause decision tree, where the global root cause decision tree is to be shared by at least two of the plurality of network operators. The RCA controller requests storage of the new node in a distributed ledger that is shared by network operators. The RCA controller participates in a verification operation of the new node. In response to determining that the verification operation is successful, the RCA controller adds an entry including the new node to the distributed ledger as part of the global root cause decision tree. Alternatively, when the verification operation is not successful, the new node is not added to the distributed ledger.

Abstract: A method in a control unit for configuration in a wireless communication system is provided. A service category is mapped to a virtual network instance based on service requirements of the service category, the virtual network instance having a first virtual network instance configuration for a current time interval, the first virtual network instance configuration defining a first allocation of resources in a plurality of network layers. A network state in a next time interval is predicted and it is determined if the predicted network state results in a predicted performance degradation in the next time interval. On condition that there is a predicted performance degradation, a second virtual network instance configuration is determined for the next time interval. The virtual network instance is configured based on the first network instance configuration or the second network instance configuration.

Abstract: AM and LM parameters to be used for adapting an ASR model are derived for each audio segment of an audio stream comprising multiple audio programs. A set of identifiers, including a speaker identifier, a speaker domain identifier and a program domain identifier, is obtained for each audio segment. The set of identifiers are used to select most suitable AM and LM parameters for the particular audio segment. The embodiments enable provision of maximum constraints on the AMs and LMs and enable adaptation of the ASR model on the fly for audio streams of multiple audio programs, such as broadcast audio. This means that the embodiments enable selecting AM and LM parameters that are most suitable in terms of ASR performance for each audio segment.

Abstract: A method for managing allocation of network resources at a site in a communication network is disclosed. The method is performed by a resource manager and comprises receiving a notification of an event occurring at a network entity, the network entity being associated with the site and with a network operator. The event comprises at least one of a performance event, a fault event or an update event. The method further comprises determining an implication of the notified event for traffic flow in the network and determining, on the basis of the implication of the notified event for traffic flow in the network, an operational requirement to compensate for the event. The method further comprises obtaining configuration information for fulfilment of the operational requirement and instructing an infrastructure manager for the site to allocate network resources in accordance with the obtained configuration information in order to satisfy the operational requirement.

Abstract: Federated learning is used to predict network communication performance at an edge node (10-1). The edge node (10-1) trains a local model (14-1) of network communication performance over one or more rounds of training, based on a local training dataset (22-1) and based on multi-node training information (20-1) received in each round of training. This information (20-1) comprises In information about local models (14-2, . . . 14-N) at other respective edge nodes (10-2, . . . 10-N) as trained based on local training datasets at the other edge nodes (10-2, . . . 10-N). After or as part of each round of training, the edge node (10-1) transmits control signaling that indicates an accuracy of the local model (14-1) as trained through that round of training, that indicates whether another round of training is needed or desired, and/or that indicates whether any further information (20-1) is needed or desired.

Abstract: Methods and devices enable connecting devices to cellular networks using the devices' hardware identifiers. Subscriber records include a hardware identifier assigned when the devices are manufactured. A target hardware identifier included in an attachment request is associated with an International Mobile Subscriber Identity, IMSI, available to the cellular network if, according to subscriber records, the device is registered.

Abstract: A method by a first wireless device, for determining a status of a first cell is described herein. The first wireless device operates in a communications network. The first wireless device sends a request to a plurality of second wireless devices operating in the communications network. The plurality of second wireless devices is within radio range. The request inquires whether or not the first cell is in sleeping state. The first wireless device receives, in response to the sent request, one or more responses from the plurality of second wireless devices. The first wireless device determines whether or not the first cell is in sleeping state, based on the received responses. The methods by a network node and another wireless device receiving an indication indicating a result of the determination are also described.

Abstract: A method for adapting a piece of live content includes determining a reference group including at least one reference content consumer device being associated with a reference user and including a user state device for detecting a user state; determining that the piece of live content is streamed to the content consumer devices of the reference group; obtaining, from at least one of the content consumer devices of the reference group, at least one respective emotion indicator; determining an emotion; determining a target group comprising at least one target content consumer device being associated with a target user; triggering adapting of the piece of live content based on the at least one emotion indicator and a preference; and triggering the adapted content to be delayed.

Abstract: It is provided a method for enabling prediction of a future operational condition for at least one site, each site comprising at least one radio network node of a radio access technology, RAT, of a cellular network. The method comprises the steps of: obtaining input properties of the at least one site; selecting a plurality of machine learning models based on the input properties; and activating the selected plurality of machine learning models in an inference engine, such that all of the selected plurality of machine learning models are collectively applicable to enable prediction of a future operational condition of the at least one site.