Telefonaktiebolaget Lm Ericsson (publ)

Agnes Rensfelt

Martin Skarve

David Sandberg

Pontus Arvidson

Magnus Hurd

Sven Harald Ekemark

Lena Melin

Mikael Söderström

Henrik RydÉn

Tomas Brännlund

Sven Ekemark

Tomas BRÄNNLUND

Mikael SÖDERSTRÖM

Systems and methods related to traffic flow prediction in a wireless network are disclosed. In one embodiment, a computer-implemented method comprises collecting training data comprising Internet Protocol (IP) addresses extracted from packets for traffic flows in a wireless network and one or more actual traffic type related parameters for each of the traffic flows. The method further comprises training heavy-hitter IP address encodings based on the extracted IP addresses and encoding the extracted IP addresses using the trained heavy-hitter IP address encodings. The method further comprises training a traffic type predictor of a traffic flow predictor based on the encoded IP addresses and the one or more actual traffic type related parameters for each of the traffic flows, where the traffic type predictor is a learning model that maps encoded IP addresses to one or more predicted traffic type related parameters.

Traffic flow prediction in a wireless network using heavy-hitter encoding and machine learning

A split radio access architecture comprises a packet processing node and one or more baseband processing nodes. The packet processing node receives, from a baseband processing node, first feedback corresponding to air interface congestion between the baseband processing node and a wireless device receiving packets from the baseband processing node. The packet processing node also receives, from the baseband processing node, second feedback corresponding to transport network congestion of a transport interface between the packet processing node and the baseband processing node. The packet processing node transmits user data to the baseband processing node based on the received first and second feedback.

5G congestion control

The overlay of two flow control techniques independently controls the data rate and transmission window size to control congestion in a split radio access architecture comprising a packet processing node () that provides user data to one or more baseband processing nodes (). In particular, the packet processing node () determines a data rate for providing the user data to a baseband processing node () responsive to air interface feedback received from the baseband processing node (), and determines a transmission window size for providing user data to the baseband processing node () responsive to transport network congestion feedback received from the baseband processing node (). In so doing, the solution presented herein achieves a high data throughput while also being Internet/TCP compatible.

A method for determining a priority of a mobile subscriber in a cellular network. The method is performed in a radio network node and comprises the steps of: obtaining a temporary mobile subscriber identity, TMSI, associated with a priority affecting event; storing the TMSI associated with the event, as at least part of an indication of priority; receiving a connection request from a wireless terminal of the mobile subscriber, the connection request comprising a TMSI; and determining a priority of the wireless terminal based on whether the TMSI of the connection request matches a stored TMSI or not.

Method and apparatuses for determining priority of a wireless terminal

Growing community of inventors

Bromma, Sweden

Agnes Rensfelt