Samsung Electronics Co., Ltd.

Pranav Madadi

Jianzhong Zhang

Jeongho Jeon

Vikram Chandrasekhar

Joonyoung Cho

Russell Douglas Ford

Yan Xin

Sangkyu Park

Yongseok Park

Junhyuk Song

Hakyung Jung

Mandar Narsinh Kulkarni

Eric Earl Johnson

Caleb K Lo

Shan Jin

Sparsity assisted channel state information (CSI) reporting or two-step CSI reporting is enabled or disabled for a user equipment. The configuration enabling/disabling sparsity assisted truncation for CSI reporting or two-step CSI reporting includes a domain for transformation of CSI for the sparsity assisted CSI reporting, and a time window for correlated channel. When the configuration enables sparsity assisted truncation for CSI reporting, a fixed number of non-zero coefficients and one or more threshold values for delay/angle or doppler for truncation are configured. When sparsity assisted truncation for CSI reporting is enabled, received the CSI reference signals are measured based on the configuration and a CSI report is transmitted indicating a specific range for which truncation occurred. When two-step CSI reporting is enabled, CSI compression corresponding to the at least one configuration and the time window is performed and CSI feedback is transmitted along with a flag.

Method for utilizing channel sparsity and coherence in CSI feedback

A two-dimensional constellation for data signals having improved bitwise mutual information of data points is based on a signal-to-noise ratio (SNR) and a code rate where, based on the SNR, data bits are mapped to pre-defined in-phase and quadrature values. The in-phase and quadrature values denote points in the two-dimensional space such that the efficiency of bitwise mutual information is adapted based on the SNR. The mapping is preferably subject to a constraint selected from one of quadrant symmetry Lagrangian (QSL), quadrant symmetry constraint (QSC), or rectangular structure constraint (RSC).

AI/ML empowered high order modulation

A service management and orchestration (SMO) entity enabling a functional split between a non-real-time (RT) radio access network (RAN) intelligent controller (RIC) and an external artificial intelligence (AI)/machine learning (ML) server will, during a data collection phase, utilize the SMO entity and the non-RT RIC to collect and process RAN data and non-RAN data and, during a data transfer phase, transfer processed RAN and non-RAN data from the SMO entity to an external AI/ML server via an interface. During a training model input phase, the SMO entity receives a trained AI/ML model, metadata, and training results from the external AI/ML server via an interface and, during a configuration phase, the SMO entity uses the trained AI/ML model within the SMO entity and the non-RT RIC to transfer configuration parameters to a near-RT RIC.

Functional architecture and interface for non-real-time ran intelligent controller

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 discovering and diagnosing network anomalies. The method includes receiving key performance indicator (KPI) data and alarm data. The method includes extracting features based on samples obtained by discretizing the KPI data and the alarm data. The method includes generating a set of rules based on the features. The method includes identifying a sample as a normal sample or an anomaly sample. In response to identifying the sample as the anomaly sample, the method includes identifying a first rule that corresponds to the sample, wherein the first rule indicates symptoms and root causes of an anomaly included in the sample. The method further includes applying the root causes to derive a root cause explanation of the anomaly and performing a corrective action to resolve the anomaly based on the first rule.

Root cause analysis and automation using machine learning

Growing community of inventors

Mountain View, CA, United States of America

Pranav Madadi