Telefonaktiebolaget Lm Ericsson (publ)

Huawei Technologies Co., Limited

David Sandberg

Mats Åhlander

Alexander Langereis

Björn Nordström

Anders Christensson

Patrik Rask

Torbjörn Wigren

Jonas Fröberg Olsson

Henrik Rydén

Ari Kangas

Fredrik Huss

Eric W Parsons

Henrik Olofsson

Michael Roberts

Carola Faronius

Kittipong Kittichokechai

Johan Christer Johansson

Alexey Shapin

Andreas Olsson

Magnus Persson

Saad Naveed Ahmed

Leo Hedlund

Lars Klockar

Mats Zachrison

Agnes Rensfelt

Don Corry

Pontus Arvidsson

Henrik RydÉn

Björn Nordstróm

Christer Qvarfordt

Mats ÅHlander

Björn NORDSTRÖM

Jessica ÖStergaard

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 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 method performed by a first network node is provided. The method includes determining a power backoff indicator (PBI) for a first user equipment (UE) based on at least one of channel conditions of the first UE and channel conditions of a second UE, data reliability requirements of the second UE, and data performance of the first UE. The method includes transmitting the PBI toward the first UE. The method includes receiving second data from the first UE, wherein transmission of the second data has been adjusted based on the PBI. The UE receives the PBI. Responsive to determining to apply the PBI, the UE backs off the power by adjusting the power according to at least one of a configuration and the PBI. The UE transmits second data to the first network node with the backed off or adjusted power.

UE and first network node for handling power adjustments

A method and a network node () serving a first cell in a wireless network, for reducing interference in a second cell caused by transmission of reference signals in the first cell. The network node () transmits () in the first cell a scheduling block where a number of said reference signals are located in predefined resource element positions in the scheduling block, using a time offset relative transmission of a scheduling block in the second cell. Thereby, the impact of interference from a reference signal from one network node will be distributed over several resource elements in the other network node so that the impact in each resource element is reduced, as compared to when all interference from the reference signal hits one single resource element when no time offset is used.

Method and network node for reducing interference in a wireless network

A method and a first network node () serving a first cell (A) in a wireless network, for enabling reduction of interference in a second cell (B) caused by transmission of reference signals in the first cell (A). The first network node () transmits () scheduling blocks with said reference signals, using a time offset relative transmission of scheduling blocks in the second cell. A timing advance value is determined () for a wireless device () and the wireless device () instructed () to apply said timing advance value for uplink transmissions. The timing advance value was determined such that uplink symbols transmitted from the wireless device () are aligned with uplink symbols received at a second network node () of the second cell (A).

Method and network node for enabling reduced interference in a wireless network

A method performed by a node in a wireless communication network of estimating parameters used for determining a signal-to-interference measure at a communication device served by a base station, and a node performing the method. The method comprises acquiring an estimate of channel condition between the communication device and the serving base station, and between the communication device and at least one base station of a neighbouring cell, estimating the signal-to-interference measure using the estimate of the respective channel condition, and acquired output power and Physical Resource Block (PRB) utilization of each of the base stations, and receiving an indication of quality of a channel via which the communication device is served by the base station. The method further comprises determining whether a change in the estimate of the signal-to-interference measure is required based on the indication of channel quality, and updating the estimate of the channel condition.

Estimation of parameters used for determining a signal-to-interference measure at a wireless communication device

A network node and a method performed thereby for supporting VoIP service of a wireless device are provided. The network node is operable in a wireless communication network, and the method comprises, when a channel quality of a channel between the wireless device and the network node falls below a predetermined threshold: determining () QoS requirements with regard to GBR for services which the wireless device is currently using; determining () an achievable bitrate using TTI bundling; and determining () to enable TTI bundling of the wireless device based on the determined aggregated GBR requirement and the determined achievable bitrate.

Network node and method performed thereby for supporting VoIP service of wireless device

In a method for downlink link adaptation in a network node in a communication system, the network node serving a cell and active user equipment within the cell, performing the steps of obtaining uplink path gain and downlink SINR for at least a subset of active user equipment in the cell, estimating an initial downlink SINR for new user equipment in the cell, based on an estimated uplink path gain together with a determined statistical measure for the obtained uplink path gain and downlink SINR for the at least a subset of active user equipment in the cell, and utilizing the estimated initial downlink SINR for downlink link adaptation for a subsequent transmission to the new user equipment.

Fast initialization of downlink adaptation

It is presented a method for releasing semi-persistent scheduling, SPS, for a wireless device. The method is performed in a network node and comprising the steps of: transmitting an SPS release message to the wireless device to release uplink SPS; starting a timer; when a first condition is true, transmitting a grant for uplink transmission to the wireless device, the first condition being true when the timer expires and/or a scheduling request has been received from the wireless device; receiving a data type indication from the wireless device; and determining that an SPS release message has been correctly received by the wireless device when a scheduling request has been received from the wireless device, the grant has been transmitted and the data type indication indicates only voice over internet protocol, VoIP, data from the wireless device.

Release of semi-persistent scheduling

Methods and apparatus for uplink power control in a communication system with a low power cell neighboring a macro cell. The low power cell includes a low power node serving a user equipment (UE). The macro cell includes a base station serving one or more other UE(s). The low power node is configured to determine a power offset between the macro cell and the low power cell. The received power spectral density target for the UE calculation is based on the minimum of a first signal strength target for the UE and estimated noise and interference power(s), or a second signal strength target for the UE and the calculated power offset. The uplink power control for the UE is adjusted based on the calculated received power spectral density target. The first signal strength target may be based on the signal-to-interference-plus-noise ratio target for the UE and the second signal strength target may be based on a signal strength derived from a signal-to-noise ratio target for the UE.

Uplink power control in heterogeneous networks

Disclosed is a network node and a method performed by a network node in a wireless communication network for determining signal to noise ratio of a signal received at a receiver from a first mobile station, which signal may include both noise and interference. The method comprises obtaining a plurality of measured noise and interference power values, IN values, of signals received at the receiver in one or more frequency sub-bands, determining IN for a lowest X percentile of the measured IN values, and applying the determined IN for the lowest X percentile as a measure of the noise. The method further comprises obtaining a measured signal strength value for a signal received at the receiver from the first mobile station, and determining SNR for the signal from the first mobile station by applying the determined noise measure.

Method, network node and computer program for determining signal to noise ratio, and method, network node and computer program for controlling transmission of delay sensitive data in a communication network

A method performed by radio network node for enabling channel handling of a channel between a wireless device and the radio network node in a wireless communication network. The channel is defined in continuous time and a sampling rate of the channel is non-uniform. The radio network node predicts a channel gain using a first sampling descriptor indicating a first momentary sampling frequency and a second sampling descriptor indicating a second momentary sampling frequency, wherein the first sampling descriptor operates on a different segment of continuous time than the second sampling descriptor. The predicted channel gain enables channel handling such as channel estimation and link adaptation.

Radio network node and method performed therein

It is presented a method for controlling cyclic shift for demodulation reference symbols for uplink communication in a cellular communication network. The method is performed in a network node and comprises the steps of: determining a first cyclic shift parameter for demodulation reference symbols based on a current subframe index; generating a control message comprising the first cyclic shift parameter; and transmitting the control message to a wireless device of the cellular communication network. Corresponding network nodes, computer program and computer program product are also presented.

Controlling cyclic shift for demodulation reference symbols

The teachings relate to a methodperformed in a network nodefor determining a link adaptation parameter, SINR, for a wireless device. The network nodesupporting a multi-antenna transmission mode comprising spatial multiplexing layers for transmission of data on a channel between the wireless deviceand the network node. The methodcomprises: determininga channel covariance matrix HH for the channel, wherein H is the channel matrix for the channel; approximatinga post-equalizer signal to interference plus noise ratio SINR., for a spatial multiplexing layer i using the channel covariance matrix HH; determiningan offset SINR, i to be the difference between a received signal to interference plus noise ratio SINRand the approximated post-equalizer signal to interference plus noise ration SINR, and determiningthe link adaptation parameter SINRto be the approximated post-equalizer signal to interference plus noise ratio SINRcompensated by the determined offset SINR. Corresponding network node, computer program and computer program products are also provided.

Methods and devices for determining link adaptation parameters

A method and apparatus for determining when to switch between buffer estimation states for a fixed frame rate services session at a terminal. In the event that the state is passive, a network node determines a first time between two received Radio Link Control Service Data Units (RLC SDU). If the first time is lower than a first time threshold, then the state is changed to proactive. When the state is proactive, the network node determines that two consecutive padding transport blocks have been received and further determines that a second time between two padding transport blocks is greater than a second time threshold. If so then the state is changed to passive.

Growing community of inventors

Solna, Sweden

David Sandberg