Samsung Electronics Co., Ltd.

Nec Laboratories America, Inc.

Future Wei Technologies, Inc.

Dongguk University Industry-Academic Cooperation Foundation

Huawei Technologies Co., Limited

Yan Xin

Jianzhong Zhang

Young-Han Nam

Hao Chen

JongSoo Choi

Samuel Albert

Sampath Rangarajan

Nandu Gopalakrishnan

Vishnu Vardhan Ratnam

Mandar Narsinh Kulkarni

Russell Douglas Ford

Md Saifur Rahman

Yang Li

Guosen Yue

Gang Xu

Rubayet Shafin

Sangkyu Park

Jin Yang

Jong-Soo Choi

Yongxi Tan

Yanjie Fu

Kyungtae Kim

James Matthew

Mehmet N Kurt

Zhou Zhou

Eko Nugroho Onggosanusi

Younsun Kim

Joon-Young Cho

Ju-Ho Lee

Boon Loong Ng

Vikram Chandrasekhar

Krishna Kamal Sayana

Honghai Zhang

Hakyung Jung

Young Han Nam

Robert W Monroe

Jin Yuan

Seung-Hoon Hwang

Pranav Madadi

Iyad Alfalujah

Ioannis Tzanidis

James Mathew

Han Wang

Kamalaharan Dushyanthan

Byoung-Jo Choi

Lianjun Li

Semih Yagli

Robert Monroe

A method for performing mobility load balancing includes receiving, at a server, current load data for a plurality of cells of a wireless communication network, selecting, from the plurality of cells, a target cell (s), wherein a value of the current load data for the target cell exceeds a first predefined threshold, and selecting, from a neighbor cell list corresponding to the target cell, a set of neighboring cells for the target cell. The method further includes calculating, a value of at least one utilization parameter for the target cell, determining, a CIO value and an E-tilt value for the target cell based on the value of the at least one utilization parameter for the target cell and configuring one or more physical layer parameters of the target cell based on the determined CIO and E-tilt values for the target cell.

Methods and apparatus for network load balancing optimization

Methods and apparatuses for automating configuration management in cellular networks. A method of a UE comprises: training, based on historical samples, a regression model y using samples obtained from a set of parameters, wherein the regression model y comprises a function of a first term X and a second term h; and predicting, based on the regression model y, a target KPI to capture parameter impacts corresponding to the second term h.

Automating configuration management in cellular networks

A method includes partitioning a set of configuration management (CM) data for one or more cellular network devices into multiple distinct time intervals, each time interval associated with a distinct set of CM settings at the one or more cellular network devices, the CM data comprising multiple CM parameters. The method also includes determining a regression model based on the set of CM data. The method also includes applying the regression model to compute a distinct set of scores and compare the set of scores to estimate whether a performance of the one or more cellular network devices has changed during a second time interval relative to a first time interval.

Automatically using configuration management analytics in cellular networks

A method for performing line-of-sight (LoS)/non-line-of-sight (NLoS) filtering includes collecting, from at least one user equipment (UE) operating within a coverage area of a base station, a plurality of measurement reports from the at least one UE, wherein each measurement report of the plurality of measurement reports comprises a measured value of a signal parameter and location information of the at least one UE. The method further includes training a LoS/NLoS classification model on the plurality of measurement reports, obtaining a new measurement report from a UE operating at a first location within the coverage area of the base station and passing the new measurement report from the UE to the trained LoS/NLoS classification model to obtain a LoS/NLoS classification of the first location.

Line of sight (LoS)/non-line of sight (NLoS) point identification in wireless communication networks using artificial intelligence

A network management apparatus of a wireless network includes a network interface, a processor, and a memory. The memory contains instructions, which when executed by the processor, cause the apparatus to receive, via the network interface, first data comprising values of key performance indicators (KPIs) obtained from elements of the wireless network for a first time period, receive, via the network interface, second data comprising values of key quality indicators (KQIs) for the first time period, wherein the KQIs comprise metrics of end-user quality of service (QoS) of the wireless network, and perform supervised learning to train an artificial intelligence (AI) model based on the first and second data, wherein features of the AI model are based on KPIs available from elements of the wireless network, and outputs of the AI model comprise values of one or more KQIs.

System and method for artificial intelligence (AI) driven voice over long-term evolution (VoLTE) analytics

A system and method of a base station are configured to enable a multi-shot network parameter optimization. The method includes generating one or more specified Key Performance Indicators (KPI) constraints based on a selected set of KPIs. The method also includes adjusting common beam parameters to tune a common beam based on the selected set of KPIs. The common beam is tuned to satisfy the one or more specified KPI constraints. The method also includes adjusting handover A2 and A5 parameters based on searching within a three-dimensional space defined by specified A2 and A5 thresholds. The method further includes transmitting one or more signals based on the adjusted the common beam parameters and the adjusted handover A2 and A5 parameters.

Methods and apparatus for multi-shot network parameter optimization

Apparatuses and methods for identifying network anomalies. A method includes determining a cumulative anomaly score over a predefined time range based on a subset of historical PM samples and determining an anomaly ratio of a first time window and a second time window, based on the cumulative anomaly score. The method also includes determining one or more anomaly events coinciding with CM parameter changes based on the anomaly ratio; collating the PM, alarm, and CM data into a combined data set based on matching fields and timestamps; generating a set of rules linking one or more CM parameter changes and the collated data to anomaly events; and generating root cause explanations for CM parameter changes that are linked to anomaly events.

Configuration management and analytics in cellular networks

A method for operating a base station is provided. The method includes in response to a triggering event, fetching information on a base station (BS) configuration parameters comprising a location, a height, an antenna pattern, and topographical details surrounding the BS; determining the BS configuration parameters that are error prone and require re-estimation; obtain measurement reports created by at least one user equipment (UE); determining an audit method to perform an audit correction, the audit correction based on the one or more of the BS configuration parameters to re-estimate, available BS information and the measurement reports; performing the audit correction, to obtain a result based on a computed score for each candidate value of the BS configuration parameters; generating, based on the result, one or more corrective actions; and adjusting at least one of the BS configuration parameters based on the one or more corrective actions.

Method and apparatus for base station audit correction in wireless communication networks

A core network entity (CNE) can predict received signal strength values for base station (BS). In response to a triggering event, the CNE fetches information on BS configuration parameters, including at least one of: a BS class, a BS location, a BS height, an orientation of the BS, a BS antenna pattern, and topographical details surrounding the BS. The BS obtains, processes and forwards to the CNE, measurement reports created by a user equipment (UE) including a signal strength value and a location of the UE. The CNE pools the measurement reports based on the BS class and, in response to another triggering event, recalibrates signal strength prediction tools, which can predict received signal strength values from the BS to a location in a vicinity of the BSs. The CNE also pools and stores the measurement reports and corresponding BS configuration parameters, after post processing and compression.

Generating and calibrating signal strength prediction in a wireless network

Convergence times associated with simulated annealing based (SA-based) optimization in wireless networks can be reduced by introducing an additional local or cell-level evaluation step into the evaluation of global solutions. In particular, new local solutions may be evaluated based on local performance criteria when the new solutions are in a global solution deemed to have satisfied a global performance criteria. New local solutions that satisfy their corresponding local performance criteria remain in the new global solution. New local solutions that do not satisfy their corresponding local performance criteria are replaced with a corresponding current local solution from a current global solution, thereby modifying the new global solution. The resulting modified global solution includes both new local solutions and current local solutions prior to being accepted as the current global solution for the next iteration.

Autonomous, closed-loop and adaptive simulated annealing based machine learning approach for intelligent analytics-assisted self-organizing-networks (SONs)

A method for operating a large scale antenna array in a wireless communication system includes receiving one or more signals. The one or more signals include information for beamforming to a plurality of user equipments (UEs) using a full-dimensional multiple-input multiple-output (FD-MIMO) beamforming scheme. The FD-MIMO beamforming scheme includes same time resources and same frequency resources that are co-scheduled to the plurality of UEs. The method further includes identifying a time delay of the one or more signals associated with one or more antenna arrays that are distributed in the large scale antenna array and performing a multi-user (MU) joint beamforming on the one or more signals to one or more UEs.

2D active antenna array operation for wireless communication systems

A method for mitigating interference in a wireless communication system includes receiving a signal transmitted from a mobile station, subtracting a target signal within a target bandwidth (BW) from the received signal to obtain a resultant signal, wherein the target signal is constructed by estimating a target channel and target symbols from the signal, determining a subspace blind interference sensing (BIS) BW by extending resource blocks (RBs) prior to a starting RB and after an ending RB of the target bandwidth using energy detection in each RB, determining a set of candidate interfering BWs in the subspace BIS BW by determining the number of interferers in each RB in the subspace BIS BW, and determining a set of candidate interfering DMRS sequences based on the set of candidate interfering BWs by performing DMRS detection for each candidate interfering BW.

Apparatus and method for mitigating interference in a wireless communication system

A multistage beamforming circuit includes a data unit that implements a frequency domain beamforming stage and a remote radio head that implements a time-domain broadband beamforming stage. The data unit implements the frequency domain beamforming stage by converting K received data streams into M precoding output streams in a frequency-domain. The data unit is configured to transform the M output streams to M OFDM time-domain signals. The remote radio head, or integrated radio unit is configured to implement a time-domain broadband beamforming stage by converting the M OFDM time-domain signals into N transmit streams of time-domain samples. The remote radio head, or integrated radio unit includes a transmit antenna array configured to transmit the N transmit streams that together form broadcast beams and user-specific beams. The antenna array includes a plurality of physical antennas. The number N of transmit streams is greater than the number M of precoding output streams.

Multistage beamforming of multiple-antenna communication system

Adjusting cell specific antenna configuration parameters includes receiving, at each of a plurality of radio access nodes in a network, measurement reports from a plurality of user equipment devices. Base incremental adjustments to configuration parameters of one or more antennas are performed at each radio access node in response to the measurement reports. Additional measurement reports are received from the plurality of user equipment devices after the incremental adjustments. Base incremental adjustments to the configuration parameters of the one or more antennas at the radio access nodes continue to be performed in response to the measurement reports after previous incremental adjustments until an improvement limit has occurred. Biased random adjustments to the configuration parameters of the one or more antennas at the radio access nodes are performed in response to the improvement limit until a desired optimum result is achieved.

Method and apparatus for optimizing cell specific antenna configuration parameters

Channel quality indicator (CQI) and precoding feedback from a user equipment includes reporting of at least a first and a second precoding matrix indicator (PMI). First, second and third indices are determined based upon the first and the second PMI and third and fourth PMI and are employed to select the precoding matrix. The selected precoding matrix includes a first column comprising a first row partition and a second row partition, where the first row partition is a Kronecker product of at least first and second precoding vectors and the second row partition is a Kronecker product of a first term and a second term. The first term is a product of a co-phasing factor and the first precoding vector and the second term is the second precoding vector. The first precoding vector is selected from a first codebook and the second precoding vector is selected from a second codebook.

Precoding matrix codebook design and periodic channel state information feedback for advanced wireless communication systems

Growing community of inventors

Princeton, NJ, United States of America

Yan Xin