Nokia Solutions and Networks Oy

Motorola Mobility LLC

Google Inc.

Nokia Technologies Oy

Nokia Siemens Networks Oy

Orange

Suresh Kalyanasundaram

John McFarland Harris

Rajeev Agrawal

Anand Bedekar

Balamurali N Natarajan

Richa Gupta

Venkat Gopikanth

Shalini Gulati

Veronique Capdevielle

Hans Juergen Kroener

Lorenzo Maggi

Hua Xu

Vinod Kumar Ramachandran

Afef Feki

Xiaoyi Wang

Claudiu Mihailescu

Klaus Ingemann Pedersen

Takeshi Tanaka

Troels Emil Kolding

Claudio Rosa

Ivan Vukovic

Eugene Visotsky

Jakob Hoydis

Shirish Nagaraj

Tsunehiko Chiba

Bishwarup Mondal

Nidham Ben Rached

Jay P Jayapalan

Philippe R Sehier

Liang Xing

Masatoshi Nakamata

Rangsan Leelahakriengkrai

Jani Matti Johannes Moilanen

Joseph Olk Lester

Chandrasekar Sankaran

Guang Han

Vishnu Ram Ov

Naveen Arulselvan

Deepak Kumar Nayak

Manjari Chhawchharia

Chandrashekhar Thejaswi

Tilman Felgentreff

Francis Dominique

Muhammad Ayyaz Qureshi

Karthik Kuntikana Shrikrishna

Martin Steiert

Jinesh P Nair

Vihang Gangaram Kamble

Richa Dham

Igor Filipovich

Jamil Shihab

Fahad Syed Muhammad

Qiaobing Xie

Ian Dexter Garcia

Qi Liao

Alvaro Valcarce Rial

Shivanand Kadadi

Ilaria Malanchini

Alois Herzog

Zwi Altman

Moushumi Sen

Raghavendra M Ramakrishna

Saikat Saha

Lele Shen

Vihang G Gangaram Kamble

Bala Venkata Ramulu Gorantla

Rakshak Agrawal

Sheshachalam B S

Deepak Nayak

Sheshachalam Bangalore Satyanarayana

Boris Kouassi

Ram O V Vishnu

Hans Kroener

Maggi Lorenzo

Joseph Lester

Vihang Gangaram G Kamble

A deep transfer reinforcement learning (DTRL) method based on transfer learning within a deep reinforcement learning (DRL) framework is provided to accelerate the GoB optimization decisions when experiencing environment changes in the same source radio network agent or when being applied from a source radio network agent to a target radio network agent. The transferability of the knowledge embedded in a pre-trained neural network model as a Q-approximator is exploited, and a mechanism to transfer parameters from a source agent to a target agent is provided, where the transferability criterion is based on the similarity measure between the source and target domain.

Apparatus, method and computer program for accelerating grid-of-beams optimization with transfer learning

A method includes obtaining elevation angle information for a plurality of user devices, wherein the elevation angle information includes, for each of the plurality of user devices, a best or preferred beam elevation angle used or applied by a network node for communication with the user device; estimating an elevation angle distribution for the plurality of user devices based on the collected elevation angle information; determining, based on the elevation angle distribution, a set of analog beamforming weights to be used for hybrid beamforming, wherein each analog beamforming weight of the set of analog beamforming weights is associated with an analog elevation angle; and adjusting the set of analog beamforming weights based on at least one of a set of pre-tilt angle beamforming weights or an estimated (or an estimate of) mechanical downtilt angle.

Selection of set of analog beamforming weights for hybrid beamforming within wireless networks

An apparatus, method and computer program is described above: determining a coupling gain for a user device within a cell of a mobile communication system; comparing the determined coupling gain with a coupling gain threshold; setting the user device to operate in a device-specific CSI-RS mode of operation in the event that the determined coupling gain is less than the coupling gain threshold, wherein, in the device-specific CSI-RS mode of operation, the user device is configured to use device-specific reference signal transmissions for the determination of channel state information; and setting the user device to operate in a cell-specific CSI-RS mode of operation in the event that the determined coupling gain is not less than the coupling gain threshold, wherein, in the cell-specific CSI-RS mode of operation, the user device is configured to use cell-specific reference signal transmissions for the determination of channel state information.

Method and apparatus for controlling operation of user device

An apparatus for a communication system, the apparatus comprising at least one processor, and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to: determine a first measurement of first reference signals associated with a first analog beam used to receive the first reference signals, determine a second measurement of second reference signals associated with a second analog beam used to receive the second reference signals, determine first information characterizing a digital beamformer based on the first measurement and the second measurement.

Apparatus and method for a communication system

Beam and antenna array split configuration optimization is disclosed. A network node device generates a beam dictionary defining a set of beams. The network node device estimates a traffic density distribution for a radio channel based on obtained channel quality information. The network node device determines, for each of at least two array split configurations associated with a transceiver antenna array of the network node device, a set of optimal beams from the beam dictionary that optimizes a utility function, based on the estimated traffic density distribution. The network node device selects an array split configuration that maximizes the utility function across a coverage area of a radio cell associated with the network node device. The network node device applies the selected array split configuration to the transceiver antenna array in response to evaluating that the selected array split configuration improves downlink performance.

Beam and antenna array split configuration optimization

A method and apparatus determine a transmission beam for downlink transmissions, and provides first beamforming instructions for forming the transmission beam to a transmission path. The method and apparatus also determine at least one receiving beam that is a first receiving beam, and at least one receiving beam that is a second receiving beam. A first antenna sub-array is configured to provide a first plurality of concurrent receiving beams and a second antenna sub-array is configured to provide a second plurality of concurrent receiving beams, providing second beamforming instructions, for forming at least the first receiving beam and at least the second receiving beams, to a first receiving path and a second receiving path, respectively.

Hybrid beamforming for uplink transmission

Systems, methods, apparatuses, and computer program products for multi-user (MU) multiple-input multiple-output (MIMO) user pairing selection are provided. One method may include selecting multi-user multiple input multiple output (MU MIMO) candidate beams using deep neural network(s) (DNNs), and selecting paired users based on the selected beams. The deep neural network(s) (DNNs) are trained to maximize multi-user priority metric (MU-PM) or a heuristic of the multi-user priority metric (MU-PM).

Methods and apparatuses of multi-user multiple-input multiple-output beam selection and user pairing using deep learning

A method includes estimating an uplink channel for a terminal device, based on an amount of antennas used by an access node for transmitting signals to the terminal device, antennas used for receiving the transmitted signals at the terminal device, and sub-bands used for transmitting the signals. Based on the estimation, a channel covariance matrix is determined for a precoder comprised in a transmitter of the access node by determining a limited number of elements of a full dimensional channel covariance matrix, which is different than the channel covariance matrix. The limited number of elements are elements corresponding to i-th row and j-th column of the channel covariance. Correlation computation is performed for the limited number of elements. Elements of the full-dimensional channel covariance matrix that are excluded from the limited number of elements are determined and set to be zero. Precoding is performed using the determined channel covariance matrix.

Determining covariance using a lossy compression method

A method comprises selecting a beam to be scheduled for a slot that is upcoming, and selecting a terminal device to be scheduled in the selected beam. Selection of the terminal device is based on the terminal device considering the selected beam as its best beam. Physical resource blocks are allocated to the terminal device, and a beam configuration to be used for the selected beam is chosen based in part on user traffic and load distribution. A switching event is triggered. The switching event comprises producing the chosen beam configuration by providing a beamforming command and using a control line controlling a switch network comprised in phase shifters to steer the beam. The phase shifters are comprised in a radio frequency front-end unit comprising a plurality of antenna columns. The phase shifters are placed in front of selected antenna sub-arrays comprised in the plurality of antenna columns.

Hybrid beamforming

Embodiments of the present disclosure relate to a method, an apparatus and a computer readable storage medium for generating soft-decision information for a receiver. In example embodiments, a method is provided. The method includes receiving, at a first device, a signal from a second device, the signal corresponding to a group of symbols transmitted from the second device; determining, by performing Lattice Reduction linear detection on the signal, a first group of estimated symbols for the group of symbols; determining, by performing iterative interference cancellation on the first group of estimated symbols, a second group of estimated symbols for the group of symbols; and generating, based on the second group of estimated symbols, soft-decision information about the group of symbols for use by a decoder at the first device. Embodiments of the present disclosure can improve the receiver performance with reduced complexity.

Soft-decision information generation for receiver

An apparatus including an input configured to receive at least one notification from at least one radio access network node controller, the at least one notification caused to notify the apparatus of at least one physical channel assignment policy indication; an assigner configured to implement at least one physical channel assignment based on the at least one physical channel assignment policy indication; an output configured to generate and transmit at least one assignment notification to at least one user equipment associated with the apparatus, the assignment notification caused to notify the at least one user equipment of the at least one physical channel assignment.

Resource allocation policy signaling

Various example embodiments may relate to link adaptation. An apparatus may determine a first signal quality estimate for a signal. The apparatus may further determine a BLER estimate based on acknowledgements or decoding results for data blocks of the signal. The apparatus may further determine a second signal quality estimate for the signal based on the BLER estimate. The apparatus may further determine a signal quality offset based on a difference between the first signal quality estimate and the second signal quality estimate. The apparatus may further determine transmission parameter(s) for at least one subsequent data block based on the first signal quality estimate and the signal quality offset.

Dynamic error rate target for link adaptation

An apparatus including: a MIMO antenna for transmitting beamformed signals on a plurality of beams using a common frequency- and time-limited physical channel resource; circuitry for computing a beamforming gain of each beam in each sub-sector in a coverage area of said plurality of beams; circuitry for determining a beam dominance region of each beam within the coverage area of said plurality of beams; circuitry for determining, within the dominance region of each beam, an average of the beamforming gain of each of the other beams at least partially co-locating within said beam dominance region; circuitry for determining inter-beam interference estimations as an average interference of each beam from each of said other beams; and circuitry for scheduling transmissions of the beams by said MIMO antenna on said common frequency- and time-limited physical channel resource based on said inter-beam interference estimations.

Method for determining beam interference

According to an aspect, there is provided an apparatus for performing the following. The apparatus is configured to, first, allocate one or more of a plurality of available physical resource blocks to a plurality of terminal devices, wherein the allocating is performed so that a power spectral density for the plurality of terminal devices matches or exceeds a pre-defined limit or a plurality of respective pre-defined limits for power spectral density. In response to one or more physical resource blocks being still available following said allocating, the apparatus is configured to further allocate at least one of the one or more physical resource blocks still available to at least one of the plurality of terminal devices, wherein the further allocating is performed so that at least a pre-defined value for a modulation and coding scheme index is sustainable for said at least one of the plurality of terminal devices.

Power spectral density aware uplink scheduling

Disclosed is a method for determining open loop power control parameters. A first set of key performance indicators associated with a first set of open loop power control parameters is obtained from one or more first base stations. A statistical model is determined based at least partly on the first set of key performance indicators and the first set of open loop power control parameters. A second set of open loop power control parameters is determined based at least partly on the statistical model.

Determining open loop power control parameters

Growing community of inventors

Bengaluru, India

Suresh Kalyanasundaram