Abstract: A computing device in a network receives, into a machine learning model, a value for a prediction horizon, Tw, that defines a future time interval for generating predicted data corresponding to an element in a model region. Machine learning training data is received that includes data corresponding to previous element activity in the model region, which includes at least one model cluster, and wherein each of the at least one model cluster includes a plurality of adjacent model cells. Using the machine learning model, model cell parameters are generated defining a cell size and a cell geometry. Using the machine learning model, model cluster parameters are generated that include a cluster geometry, a cluster centroid value identifying a center of the model cluster and a cluster radius value defining a quantity of model.

Abstract: In a communication system, a first network node is configured to execute at least one service application executing a first service and at least one analytics application executing at least part of a distributed analytics service. The first network node obtains information about a new telecommunication service and transmits, to a second network node in the communication system, a request for a policy for the new telecommunication service. The first network node receives, from the second network node, the policy for the new telecommunication service and updates a currently applied policy on the basis of the received policy. The updated policy rebalances resources allocated from a shared computing resource pool of the first network node between the new telecommunication service and the at least one analytics application such that the new telecommunication service maintains adherence to the one or more requirements of a service level agreement.

Abstract: It is presented a method for enabling allocation of resources for a plurality of hosts. The method is performed by a server (1) and comprises identifying (S100) a service running on one or more of the plurality of hosts, determining (S140) a stretch factor for a recurring load pattern for the service running on the one or more of the plurality of hosts, and storing (S150) the identified service together with the determined stretch factor. It is also presented a server, a computer program and a computer program product.

Abstract: A method performed by a network computing device in a telecommunications network for adaptively deploying an aggregated machine learning model and an output parameter in the telecommunications network to control an operation in the telecommunications network. The network computing device can aggregate client machine learning models and an output performance metric the client machine learning models to obtain an aggregated machine learning model and an aggregated output performance metric. The network computing device can train a network machine learning model with the aggregated output performance metric and at least one measurement of a network parameter to obtain an output parameter. The network computing device can send to the client computing devices the aggregated machine learning model and the output parameter of the network machine learning model. A method performed by a client computing device is also provided.

Abstract: A method of allocating cloud computing resources in a cloud computing environment to a user is disclosed. The method comprises determining a prediction accuracy score for each user indicative of their user predictability, and allocating cloud computing resources to each user dependent on their user predictability.

Abstract: Eyewear (100) comprising at least one lens (110,120), a lens frame (111,121), a battery (170) and means for wireless charging of said battery (170), which wireless charging means comprises a receiver coil (181) arranged to be remotely powered by a corresponding transmitter coil (340) in a separate charging device (300). The invention is characterised in that the receiver coil (181) is arranged so that it encircles at least one of said one or several lenses (110,120), forming part of or being enclosed in said lens frame (111,121), whereby light passing through the at least one lens (110,120) will also pass through a coil hole.

Abstract: In a communication system, a first network node is configured to execute at least one service application executing a first service and at least one analytics application executing at least part of a distributed analytics service. The first network node obtains information about a new telecommunication service and transmits, to a second network node in the communication system, a request for a policy for the new telecommunication service. The first network node receives, from the second network node, the policy for the new telecommunication service and updates a currently applied policy on the basis of the received policy. The updated policy rebalances resources allocated from a shared computing resource pool of the first network node between the new telecommunication service and the at least one analytics application such that the new telecommunication service maintains adherence to the one or more requirements of a service level agreement.

Abstract: A method for dynamically configuring a network is proposed for training a machine learning model. The network includes a server computing device and a plurality of client computing devices. The method is performed at a computing device communicatively coupled to the network and includes the following: selecting client computing devices to participate in training the model; determining a first value of an evaluation metric of the model based on the selected client computing devices; determining the presence of an adjustment trigger; adjusting the number of client computing devices used to determine the value of the evaluation metric in response to the adjustment trigger; determining a second value of the evaluation metric based on the adjusted number of client computing devices; and setting the number of client computing devices participating in training the model accordingly.

Abstract: A method and system of filtering abnormal network parameter values are described. A network node receives first values of first network parameters that are not trusted by the network node. The network node determines, based on an expected correlation between the first values of the first network parameters and second values of second network parameters, whether the first values of the first network parameters are anomalies. Responsive to determining that the first values of the first network parameters are not anomalies, the network node causes the first values to be used as input to train a network prediction model that is used for optimization of traffic in the network, and responsive to determining that the first values of the first network parameters are anomalies, the network node causes the first values to not be used to train the network prediction model.

Abstract: It is disclosed a network node (200, 220, 300, 400, 500, 600, 80) and a method for executing an analytics task. The network node is adapted to reside in a telecommunication network, and to be supported by a distributed cloud infrastructure. The network node is adapted to execute at least one service application (202) executing a first service and at least one analytics application (204) executing at least part of a distributed analytics service, where the network node further is adapted to comprise a node policy agent (206, 226, 304, 504, 606) and a node manager (210, 230, 306, 406, 506, 608). By applying a policy restrictions on the analytics task executed on the same network node as a service application, service level agreements for the service application in a telecommunication cloud can be upheld.

Abstract: The invention relates to a method for predicting an allocation of processing resources provided by a cloud computing module (230) to process a data set based on a predefined processing task. Input parameters are detected, the input parameters containing information about at least the data set to be processed by the cloud computing module and the processing task to be carried out on the data set. A model is selected from a plurality of different models provided in a model database (130), each model providing a relationship between the data set processing task and a predicted allocation of the processing resources. The allocation of the processing resources is predicted based on the selected model and based on the input parameters.

Abstract: Eyewear (100) comprising at least one lens (110,120), a lens frame (111,121), a battery (170) and means for wireless charging of said battery (170), which wireless charging means comprises a receiver coil (181) arranged to be remotely powered by a corresponding transmitter coil (340) in a separate charging device (300). The invention is characterised in that the receiver coil (181) is arranged so that it encircles at least one of said one or several lenses (110,120), forming part of or being enclosed in said lens frame (111,121), whereby light passing through the at least one lens (110,120) will also pass through a coil hole.

Abstract: It is presented a method for enabling allocation of resources for a plurality of hosts. The method is performed by a server (1) and comprises identifying (S100) a service running on one or more of the plurality of hosts, determining (S140) a stretch factor for a recurring load pattern for the service running on the one or more of the plurality of hosts, and storing (S150) the identified service together with the determined stretch factor. It is also presented a server, a computer program and a computer program product.

Abstract: A method is provided for analyzing data storage applied on at least one data storage type. The data to be stored is transmitted in at least one data stream between at least one application instance and the at least one data storage type. The method includes accessing, from the at least one data stream, data selected according to pre-defined rules. Data access patterns are aggregated on the basis of the selected data, where the data access patterns are indicative of the at least one storage type applied. Classifiers are obtained by applying trained classifiers to the aggregated data access patterns. Differences between the obtained classifiers and the trained classifiers are analyzed to determine, that the obtained classifiers are indicative of at least one data storage type other than a presently used data storage type, in case at least one predefined threshold value is exceeded when analyzing the differences.

Abstract: A network anomaly detector detects a network anomaly by monitoring a communication network and provides an indication of the detected network anomaly to a network anomaly analyzer. The network anomaly analyzer receives the indication of the detected network anomaly and, on the basis of data representing the detected network anomaly and additional data, e.g., from outside the communication network, performs classification of the detected network anomaly. Depending on the classification of the detected network anomaly, the network anomaly analyzer provides a report of the detected network anomaly to another node. If for example the detected network anomaly is classified as expected behavior, reporting of the detected network anomaly may be suppressed.

Abstract: It is presented a method for controlling an autonomous device (4) of a cellular network (5). The method is performed by a network device (20) and comprises the steps of: predicting (43) a need to increase coverage of the cellular network or a need to increase capacity of the cellular network, comprising the steps of: inputting live data features into a trained classifier (80); and outputting a launch class from the classifier (80); and activating (45) an autonomous device (4) of the cellular network, to improve the cellular network. Corresponding network devices, computer program and computer program product are also presented.

Abstract: An approach for extending capacities of a Radio Access Network (RAN) is presented. An exemplary method implementation of that approach comprises flying a drone to an RAN site. The drone is carrying cloud computing resources that will be registered at a cloud management entity associated with the RAN. The registered cloud computing resources of the drone are then provided to the RAN to dynamically extend its capacities.

Abstract: The present invention relates to methods and devices for pre-buffering one or more content data items to be rendered at a mobile terminal. In a first aspect of the present invention, a mobile terminal (11, 12, 13) comprises a processing unit (15) arranged to acquire a probability with which at least one selected content data item of the one or more content data items is to be rendered at the mobile terminal, and to acquire an estimated point in time when the at least one selected content data item is to be rendered at the mobile terminal. Further, the processing unit is arranged to pre-buffer a first selected part of the at least one selected content data item in the mobile terminal such that the first selected part of the at least one selected content data item is ready for rendering at the estimated point in time, the extent of the pre-buffered first selected part being related to the probability with which the at least one selected content data item is to be rendered at the mobile terminal.

Abstract: Method and user equipment for requesting scheduling resources from a serving radio network node, the method comprises obtaining traffic characteristics associated with radio communication between the radio network node and the UE. The method further comprises predicting, based at least on the obtained traffic characteristics, data to arrive in a transmission buffer; and transmitting a scheduling request to the network node before said data arrives in said transmission buffer.

Abstract: A method of allocating cloud computing resources in a cloud computing environment to a user is disclosed. The method comprises determining a prediction accuracy score for each user indicative of their user predictability, and allocating cloud computing resources to each user dependent on their user predictability.