Intel Corporation

Apple Inc.

Iospan Wireless, Inc.

Stanford Telecommunications, Inc.

Shilpa Talwar

Nageen Himayat

Hosein Nikopour

Shu-Ping Yeh

Oner Orhan

Yang-Seok Choi

Feng Xue

Kerstin Johnsson

Alexander Sasha Sirotkin

Mo-Han Fong

Vivek G Gupta

Jing Zhu

Ping Wang

Debabani Choudhury

Venkatesan Nallampatti Ekambaram

Qinghua Li

Markus Dominik Mueck

Zhibin Yu

Dave A Cavalcanti

Ingolf Karls

Duncan Kitchin

Kamran Etemad

Thorsten Clevorn

Stefano Pellerano

Muthaiah Venkatachalam

Konstantinos Dimou

Christian Drewes

Srikathyayani Srikanteswara

Claudio Da Silva

Vallabhajosyula S Somayazulu

Minnie Ho

Jaroslaw Sydir

Huaning Niu

Jong-Kae Fwu

Thomas J Kenney

Xintian Eddie Lin

Bernhard Raaf

Hyung-Nam Choi

Shahrnaz Azizi

Alexandre Saso Stojanovski

Carlos Horacio Aldana

Kameran Azadet

Bryan K Casper

Marta Martinez Tarradell

Bahareh Sadeghi

Ofir Degani

Wook Bong Lee

Arogyaswami J Paulraj

Ashoke Ravi

Michael Genossar

Hassnaa Moustafa

Robert Zaus

John Joseph Browne

Bertram Gunzelmann

Biljana Badic

Simon R Hunt

Harry G Skinner

Pingping Zong

Rotem Banin

Maruti Gupta Hyde

Sidharth Dalmia

Albert Molina

Georgios Yorgos Palaskas

Saku Lahti

Igal Kushnir

Carlos Cordeiro

Debdeep Chatterjee

Emily H Qi

Minyoung Park

Justin E Gottschlich

Kathiravetpillai Sivanesan

Christian Maciocco

Jose Tellado

RongZhen Yang

Marcio Rogerio Juliato

Ana Lucia Pinheiro

Liuyang L Yang

Omesh Tickoo

Rafael Misoczki

Tom Harel

Peroor K Sebastian

Xiruo Liu

Sridhar G Sharma

Kuilin Clark Chen

Stefan Fechtel

Yuan Zhu

Po-Kai Huang

Rath Vannithamby

Candy Yiu

Murali Narasimha

Ali Taha Koc

Xue Yang

Xiangying Yang

Sumeet Sandhu

Robert Wendell Heath, Jr

Xingang Guo

Honggang Li

Yuval Shamuel Lomnitz

Ching-Yu Liao

Anthony George LaMarca

Disclosed embodiments generally relate to edge-based multi-Radio Access Technology (RAT) traffic management (TM) solutions to support delay-sensitive traffic over heterogeneous networks. Embodiments include delay-aware TM implementations that split and/or steer network traffic across different RATs for the edge network control plane. Embodiments also include utilization threshold-based implementations to achieve delay-aware multi-path TM at the network's edge. The multi-path TM includes multi-RAT, multi-access, or multi-connectivity traffic routes. Embodiments include strategies to sort users (or devices) for making multi-RAT traffic distribution decisions and to determinate the utilization thresholds. Embodiments also include message exchange mechanisms or learning utilization thresholds and other useful system properties. Other embodiments may be described and/or claimed.

Multi-radio access technology traffic management

The present disclosure is related to multi-queue management techniques and packet reordering techniques for inter-radio access technology (RAT) and intra-RAT traffic steering. The multi-queue management and packet reordering techniques may be used in Multi-Access Management Services (MAMS) framework, which is a programmable framework that provides mechanisms for the flexible selection of network paths in a multi-access (MX) communication environment, based on an application's needs. Other embodiments may be described and/or claimed.

Traffic steering and cross-layer and cross-link mobility management techniques for multi-access management services

The present disclosure provides connection management techniques based on graph neural networks (GNN) and deep reinforcement learning (DRL) to optimize user association and load balancing. A graph structure of a communication network is considered for the GNN architecture and DRL is used to learn parameters of the GNN algorithm/model. Connection management is defined as a combinatorial graph optimization problem, and the DRL mechanism uses the underlying graph to learn weights of the GNN for an optimal user connections or associations. The connection management techniques can consider local network features to make better decisions to balance network traffic load while network throughput is also maximized. Implementations are provided based on edge computing frameworks include the Open RAN (O-RAN) architecture. Other embodiments may be described and/or claimed.

Graph neural network and reinforcement learning techniques for connection management

The present disclosure is related to multi-access traffic management in multi-access computing environments. A reliability enhancement engine (REE) operated by a multi-access multipath traffic manager identifies traffic flows that have high reliability requirements ('reliability flows') and performs admission control for the reliability flows. The REE determines a coding rate (e.g., a redundancy factor) and traffic distribution strategies for the identified reliability flows. The REE applies cross-access network coding (NC) on the reliability flows, and handles multi-access acknowledgements and traffic pacing, which may involve multiplexing traffic of the reliability flows with non-high-reliability traffic. Other embodiments may be described and/or claimed.

Reliability enhancements for multi-access traffic management

Millimeter-wave (mmWave) and sub-mmWave technology, apparatuses, and methods that relate to transceivers and receivers for wireless communications are described. The various aspects include an apparatus of a communication device including an antenna array and processing circuitry coupled to the antenna array. The processing circuitry is configured to initialize a beam tracking algorithm based on received signals received at the antenna array, wherein antenna phases used in the beam tracking are bound by an upper phase limit and a lower phase limit, to generate a beam tracking result. The processing circuitry is further configured to generate a calibration vector based on the beam tracking result and receive subsequent transmissions using a codebook adapted based on the calibration vector.

Beam management and antenna calibration in MIMO systems

A computing node to implement an RL management entity in an NG wireless network includes a NIC and processing circuitry coupled to the NIC. The processing circuitry is configured to generate a plurality of network measurements for a corresponding plurality of network functions. The functions are configured as a plurality of ML models forming a multi-level hierarchy. Control signaling from an ML model of the plurality is decoded, the ML model being at a predetermined level (e.g., a lowest level) in the hierarchy. The control signaling is responsive to a corresponding network measurement and at least second control signaling from a second ML model at a level that is higher than the predetermined level. A plurality of reward functions is generated for training the ML models, based on the control signaling from the MLO model at the predetermined level in the multi-level hierarchy.

Reinforcement learning (RL) and graph neural network (GNN)-based resource management for wireless access networks

Millimeter wave (mmWave) technology, apparatuses, and methods that relate to transceivers, receivers, and antenna structures for wireless communications are described. The various aspects include co-located millimeter wave (mmWave) and near-field communication (NFC) antennas, scalable phased array radio transceiver architecture (SPARTA), phased array distributed communication system with MIMO support and phase noise synchronization over a single coax cable, communicating RF signals over cable (RFoC) in a distributed phased array communication system, clock noise leakage reduction, IF-to-RF companion chip for backwards and forwards compatibility and modularity, on-package matching networks, 5G scalable receiver (Rx) architecture, among others.

Wireless communication technology, apparatuses, and methods

The present disclosure is related to multi-access traffic management in edge computing environments, and in particular, artificial intelligence (AI) and/or machine learning (ML) techniques for multi-access traffic management. A scalable AI/ML architecture for multi-access traffic management is provided. Reinforcement learning (RL) and/or Deep RL (DRL) approaches that learn policies and/or parameters for traffic management and/or for distributing multi-access traffic through interacting with the environment are also provided. Deep contextual bandit RL techniques for intelligent traffic management for edge networks are also provided. Other embodiments may be described and/or claimed.

Reinforcement learning for multi-access traffic management

A receiver circuit associated with a communication device is disclosed. The receiver circuit comprises a digital data compression circuit configured to receive a plurality of digital receive signals derived from a plurality of analog receive signals respectively associated with the receiver circuit. The digital data compression circuit is further configured to compress the plurality of digital receive signals to form one or more compressed digital data signals based thereon, to be provided to an input output (I/O) interface associated therewith. In some embodiments, a compressed digital signal dimension associated with the one or more compressed digital data signals is less than a digital signal dimension associated with the plurality of digital receive signals.

Low power mmWave receiver architecture with spatial compression interface

The present disclosure is related to Multi-Access Management Services (MAMS), which is a programmable framework that provides mechanisms for the flexible selection of network paths in a multi-access (MX) communication environment, based on an application's needs. Generic Multi-Access (GMA) functions are also integrated into the MAMS framework. The present disclosure discusses Per-Packet Prioritization (PPP), intra-flow classification, and Active Queue Management (AQM) techniques for MAMS/GMA systems. Other embodiments may be described and/or claimed.

Multi-access management service packet classification and prioritization techniques

Various embodiments herein provide techniques for reducing computational complexity in multiple input multiple output (MIMO, e.g., massive MIMO (mMIMO)) communications, such as efficient decomposition of a channel covariance matrix. Embodiments enable accurate mMIMO channel estimation with relatively low computational complexity compared with prior techniques. Additionally, embodiments may provide efficient beamforming and/or spatial compression. Other embodiments may be described and claimed.

Techniques to improve computational efficiency in massive multiple input multiple output (MIMO) systems

An apparatus, method and computer readable medium for special thermal density reduction by antenna thinning. A system comprises N transmit/receive (TX/RX) chains, where each TX/RX chain comprises an RFFE and each RFFE comprises one or more thermal sensors configured to measure heat in the RFFE. An antenna array coupled to the plurality of TX/RX chains. A codebook that comprises a plurality of code words configured to respond to real-time heat measurements from the thermal sensors in each TX/RX chain is configured to switch off selected TX/RX chains to reduce thermal density at the antenna array while maintaining M RFFEs switched on, where M<N and the desired beamforming gain is 10 log 10(M).

Spatial thermal density reduction for MMWAVE antenna arrays

A circuit arrangement includes a preprocessing circuit configured to obtain context information related to a user location, a learning circuit configured to determine a predicted user movement based on context information related to a user location to obtain a predicted route and to determine predicted radio conditions along the predicted route, and a decision circuit configured to, based on the predicted radio conditions, identify one or more first areas expected to have a first type of radio conditions and one or more second areas expected to have a second type of radio conditions different from the first type of radio conditions and to control radio activity while traveling on the predicted route according to the one or more first areas and the one or more second areas.

Methods and devices for radio communications

Systems, apparatuses, methods, and computer-readable media, are provided for distributed machine learning (ML) training using heterogeneous compute nodes in a heterogeneous computing environment, where the heterogeneous compute nodes are connected to a master node via respective wireless links. ML computations are performed by individual heterogeneous compute nodes on respective training datasets, and a master combines the outputs of the ML computations obtained from individual heterogeneous compute nodes. The ML computations are balanced across the heterogeneous compute nodes based on knowledge of network conditions and operational constraints experienced by the heterogeneous compute nodes. Other embodiments may be described and/or claimed.

Technologies for distributing gradient descent computation in a heterogeneous multi-access edge computing (MEC) networks

Growing community of inventors

Los Altos, CA, United States of America

Shilpa Talwar