Telefonaktiebolaget Lm Ericsson (publ)

Mats Zachrison

Jonas Lennart Wiorek

Raimundas Gaigalas

Szilveszter Nádas

Sándor Rácz

Henrik Rydén

David Sandberg

Akram Bin Sediq

Peiliang Chang

Wenbiao Wu

Jonas Wiorek

Frank Müller

A method for managing a first node in a communication network is disclosed, wherein the first node is operable to exchange traffic flows with other nodes in the communication network. The method includes using a Variational Autoencoder (VAE) to generate a predicted traffic distribution for the first node, wherein the VAE has been trained using information about historical data flows exchanged by the first node with at least one other node in the communication network, and configuring at least one radio resource parameter of the first node based on the obtained predicted traffic distribution for the first node. Also disclosed are a method including training a VAE and nodes and a computer program product suitable for carrying out such methods.

Managing a node in a communication network

A network node, computer program, computer program product, and a method performed in a network node includes obtaining an estimated data amount of a user equipment, UE, and a resource utilization rate. A percentile R of the estimated data amount is obtained based on a data amount distribution table. The percentile R is compared to the resource utilization rate. Responsive to the percentile R being higher than the resource utilization rate, a resource is allocated to the UE.

Machine learning assisted user prioritization method for asynchronous resource allocation problems

A method performed by a method performed by a network node for performing admission control in a wireless communications network is provided. The network node serves a first and one or more second UEs. The network node receives () from the first UE, an access request for a radio resource for communication between the first UE and the network node. The network node further estimates () a first prediction of a requirement of the radio resource related to the access request, based on a measured initial data traffic between the network node and the first UE. The network node determines () a first threshold related to the first prediction, as a function of a measured data traffic load between the network node and the one or more second UEs. The network node then performs () admission control by deciding whether or not to admit the radio resource to the first UE, based on whether or not the first prediction exceeds the first threshold.

Network node and method in a wireless communications network

A method performed by a network node for performing Congestion Control in a wireless communications network is provided. The network node serves a number of User Equipments, UEs, comprising a first and one or more second UEs. The first UE has a radio resource allocated for communication between the first UE and the network node. The network node estimates () a first prediction of a forthcoming usage of the allocated radio resource, based on a measured data traffic between the network node and the first UE. The network node further determines () a first threshold related to the first prediction, as a function of a measured data traffic load between the network node and the number of UEs. The network node then performs () congestion control by deciding whether or not to initiate a removal of the radio resource allocated to the first UE, based on whether or not the first prediction exceeds the first threshold.

A method performed by a network node for managing a radio resource between the network node and a first User Equipment, in a wireless communications network is provided. The network node serves a number of UEs, comprising the first UE and one or more second UEs. The first UE has a radio resource allocated for communication between the first UE and the network node. The network node estimates () a prediction of a forthcoming empty data flow related to the allocated radio resource, based on a measured data flow between the network node and the first UE. The network node further determines () a threshold related to the prediction, based on a measured data flow between the network node and the number of UEs. The network node then decides () whether or not to initiate a removal of the radio resource allocated to the first UE based on whether or not the prediction exceeds the threshold.

Network node and method for deciding removal of a radio resource allocated to a UE

It is presented a method for evaluating an application intended to be installed in a wireless terminal of a cellular network. The method is performed in an application development device and comprises the steps of: obtaining performance data associated with an execution of the application in a test wireless terminal in a simulated or real cellular network, the performance data being obtained for each cellular data session of the execution of the application, each cellular data session being defined as a period when the test wireless terminal is in a cellular network connection state when data transfer is possible; and evaluating the performance data by comparing the in performance data with reference performance data, the comparison being based on the duration of each cellular data session.

Evaluation of an application

A method of controlling the rate of traffic flow through an Iub interface of a Radio Network Controller is described. The method includes obtaining a licensed rate, which defines the maximum throughput permitted through the Iub interface, at the Radio Network Controller. The rate of traffic flow through the Iub interface and all Iu interfaces of the Radio Network Controller is measured, and the extent to which packet switched traffic flow through the Iub interface exceeds the licensed rate identified. If the packet switched traffic flow through the Iub interface exceeds the licensed rate, packets are dropped from traffic flow through the Iub interface to reduce the traffic flow to the licensed rate.

Growing community of inventors

Örebro, Sweden

Mats Zachrison