Telefonaktiebolaget Lm Ericsson (publ)

Selim Ickin

Jing Fu

Leonid Mokrushin

Steven Corroy

Konstantinos Vandikas

Rafia Inam

Lackis Eleftheriadis

Tor Kvernvik

Abhishek Sarkar

Daniel Wilson

Ravi Kiran Kotty

Åsa Bertze

Tomas Lundberg

Junaid Shaikh

Farnaz Moradi

Jawwad Ahmed

Valentin Kulyk

Kaushik Dey

Ashis Kumar Roy

Wenfeng Hu

Xiaoyu Lan

Saurabh Singh

Burak Demirel

The disclosure provides methods, apparatus and machine-readable mediums for the detection of sleeping cells in a cellular network. A method of detecting a sleeping cell in a cellular communication network comprises: monitoring power consumption of a radio transmission point of the cellular communication network; providing the power consumption of the radio transmission point as an input to a classification model, developed using a machine-learning algorithm; and obtaining an output from the classification model, the output classifying the radio transmission point as serving one of a sleeping cell and a non-sleeping cell.

Methods, apparatus and computer-readable mediums relating to detection of sleeping cells in a cellular network

The disclosure provides methods, apparatus and machine-readable mediums for mitigating power failures in base stations in wireless communication networks. In one aspect of the disclosure, a method for mitigating power failures in a wireless communication network is provided. The method comprises, responsive to a determination that a primary power supply for a base station in the wireless communication network has failed or is predicted to fail, initiating deployment of an unmanned aerial vehicle to the base station to charge one or more batteries providing a secondary power supply for the base station.

Methods, apparatus and machine-readable mediums for mitigating power failures in a communication network

A method performed by a central server node in a distributed machine learning environment is provided. The method includes: managing distributed machine learning for a plurality of local client nodes, such that a first set of the plurality of local client nodes are assigned to assist training of a first central model and a second set of the plurality of local client nodes are assigned to assist training of a second central model; obtaining information regarding network conditions for the plurality of local client nodes; clustering the plurality of local client nodes into one or more clusters based at least in part on the information regarding network conditions; re-assigning a local client node in the first set to the second set based on the clustering; and sending to the local client node a message including model weights for the second central model.

Distributed machine learning using network measurements

Federated learning is used to predict network communication performance at an edge node (-). The edge node (-) trains a local model (-) of network communication performance over one or more rounds of training, based on a local training dataset (-) and based on multi-node training information (-) received in each round of training. This information (-) comprises information about local models (--N) at other respective edge nodes (--N) as trained based on local training datasets at the other edge nodes (--N). After or as part of each round of training, the edge node (-) transmits control signaling that indicates an accuracy of the local model (-) 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 (-) is needed or desired. The edge node (-) predicts network communication performance at the edge node (-) based on the trained local model (-).

Predicting network communication performance using federated learning

Methods include training, using a generative adversarial network, a generator model using data noise that includes data corresponding to real problems of a telecommunication site, generating a generated problem that has not occurred at the telecommunication site and that has a non-zero probability of occurring at the site in the future, providing the generated problem to a virtual agent that is configured to generate a solution action to resolve the generated problem, evaluating the solution action relative to the generated problem to determine a performance value corresponding to the solution action, and responsive to the performance value being higher than other performance values corresponding to other solution actions for the generated problem, generating a generic problem model that corresponds to the generated problem and that is associated with the solution action.

Improving immune system of site using generative adversarial networks and reinforcement learning

Managing network event data in a telecommunication network. The method includes obtaining a plurality of datasets having network event data associated with products provided by a different vendor, the network event data comprising a plurality of data instances representing a plurality of network event features. The method further comprises obtaining metadata describing the network event data in the datasets and generating feature description vectors from the obtained metadata, calculating a metric of the relation between network event features represented in the datasets and constructing a graph of the network event features represented in the datasets, with edges weighted according to the calculated metric, partitioning the graph into clusters by minimising an edge cut between network event features, labelling network event features in the cluster with a normalised network event feature index and inputting the labelled network event data to a model for making at least one of recommendations or predictions.

Managing telecommunication network event data

An initial bitrate is selected for a video delivery session by a user equipment () performing, during a time window from initiation of a video player application in the user equipment () up to selection of a video content, network measurements of a current condition of a network used to deliver the video content to the user equipment (). A respective initial buffer duration is provided for each bitrate available for the video content and where these respective initial buffer durations are predicted based on at least one network metric derived from the network measurements. An initial bitrate for delivering the video content over the network to the user equipment is selected based on the respective initial buffer durations.

Initial bitrate selection for a video delivery session

A method () of controlling playout of advertisement content during video-on-demand video streaming on an end-user client terminal comprising steps of: receiving () advertisement content from an advertisement server; receiving () video-on-demand, VoD, content from a content delivery network; obtaining () network quality metrics between the end-user terminal and the content delivery network; predicting () whether a stalling event will occur during playout of VoD content within a prediction time window based on the network quality metrics; and playing out () received VoD content and received advertisement content, wherein playout of advertisement content within the prediction time window is dependent on a result of the prediction.

Controlling playout of advertisement content during video-on-demand video streaming on an end-user terminal

A method and a wireless device () for handling transmission of data. The cost for transmitting the data from the wireless device () can be reduced or even minimized by delaying () transmission until the transmission cost becomes lower, provided that the data can wait without becoming obsolete or useless at the receiving side. This is made possible by determining a delay tolerance of the data and determining a cost prediction for transmission () within said delay tolerance, e.g. when a cheaper connection () is used. Advantages may include reduced price to pay for the transmission, less energy consumption, and avoided usage of precious radio resources and network resources at times when the traffic load is high.

Method and wireless device for handling transmission of data

A method () of controlling playout of advertisement content during live video streaming at an end-user terminal comprising steps of: receiving () advertisement content from an advertisement server; receiving () live streamed video content from a content delivery network and playing out the video content; obtaining () at least one of image features and audio features of the video content during playout; calculating () a content importance rating of video content to be played out during a prediction time window based on said features; and postponing () playout of advertisement content scheduled to be played out during the prediction time window if the calculated content importance rating for the prediction time window is above a threshold value.

Controlling play out of advertisement content during live video streaming at an end-user terminal

A buffer status metric representing a current amount of video packets in a video playback buffer () of a user device (). A buffer status action is triggered based on the buffer status action and at least one of a mobility metric representing a mobility pattern of the user device () and a radio quality metric representing a signal strength of a radio channel carrying video packets towards the user device (). The embodiments also relate to determination of a buffer control model () that can be used in order to control the video playback buffer based on the input metrics. The embodiments achieve a more efficient control of video playback buffers () and may reduce the risk of freezes during video playback.

Video playback buffer control

There are provided mechanisms for traffic steering between a first radio access network node and a second radio access network node. A method is performed by a system. The method includes obtaining, for each of the first radio access network node and the second radio access network node, a respective predicted traffic throughput for a wireless device. The wireless device is in dual connectivity with the first radio access network node and the second radio access network node. The method includes determining splitting of transmission of a flow of data destined for the wireless device between the first radio access network node and the second radio access network node according to the obtained predicted traffic throughputs. The method includes initiating traffic steering of the flow of data between the first radio access network node and the second radio access network node according to the splitting.

Growing community of inventors

Stocksund, Sweden

Selim Ickin