公开(公告)号：US20240155025A1

公开(公告)日：2024-05-09

申请号：US18550856

申请日：2022-06-09

Applicant: Intel Corporation

Inventor： Mustafa Riza Akdeniz ,  Arjun Anand ,  Ravikumar Balakrishnan ,  Sagar Dhakal ,  Nageen Himayat

IPC: H04L67/10 ,  G06F17/18 ,  H04L67/289

CPC classification number: H04L67/10 ,  G06F17/18 ,  H04L67/289

Abstract: An apparatus of an edge computing node, a method, and a machine-readable storage medium. The apparatus is to decode messages from a plurality of clients within the edge computing network, the messages including respective coded data for respective ones of the plurality of clients; computing estimates of metrics related to a global model for federated learning using the coded data, the metrics including a gradient on the coded data; use the metrics to update the global model to generate an updated global model, wherein the edge computing node is to update the global model by calculating the gradient on the coded data based on a linear fit of the global model to estimated labels from the federated learning; and send a message including the updated global model for transmission to at least some of the clients.

公开(公告)号：US20220377614A1

公开(公告)日：2022-11-24

申请号：US17712050

申请日：2022-04-01

Applicant: Intel Corporation

Inventor： Ravikumar Balakrishnan ,  Nageen Himayat ,  Arjun Anand ,  Mustafa Riza Akdeniz ,  Sagar Dhakal ,  Mark R. Eisen ,  Navid Naderializadeh

IPC: H04W28/08 ,  H04W28/02

Abstract: An apparatus of a transmitter computing node n (TX node n) of a wireless network, one or more computer readable media, a system, and a method. The apparatus includes one or more processors to: implement machine learning (ML) based training rounds, each training round including: determining a local action value function Qn(hn, an; θn) corresponding to a value of performing a radio resource management (RRM) action an at a receiving computing node n (RX node n) associated with TX node n using policy parameter θn and based on hn, hn including channel state information at RX node n; and determining, based on an overall action value function Qtot at time t, an estimated gradient of an overall loss at time t for overall policy parameter θt(∇Lt(θt)), wherein Qtot corresponds to a mixing of local action value functions Qi(hi, ai; θi) for all TX nodes i in the network at time t including TX node n; and determine, in response to a determination that ∇Lt(θt) is close to zero for various values of t during training, a trained local action value function Qn,trained to generate a trained action value relating to data communication between TX node n and RX node n.

公开(公告)号：US20220007382A1

公开(公告)日：2022-01-06

申请号：US17479991

申请日：2021-09-20

Applicant: Intel Corporation

Inventor： Arjun Anand ,  Ravikumar Balakrishnan ,  Vallabhajosyula S. Somayazulu ,  Rath Vannithamby

IPC: H04W72/12 ,  G06N3/08 ,  G06N3/04

Abstract: In one embodiment, an apparatus of an access point (AP) node of a network includes an interconnect interface to connect the apparatus to one or more components of the AP node and a processor to: access scheduling requests from a plurality of devices, select a subset of the devices for scheduling of resource blocks in a time slot, and schedule wireless resource blocks in the time slot for the subset of devices using a neural network (NN) trained via deep reinforcement learning (DRL).

公开(公告)号：US11218907B2

公开(公告)日：2022-01-04

申请号：US16236037

申请日：2018-12-28

Applicant: Intel Corporation

Inventor： Ravikumar Balakrishnan ,  Venkatesan Nallampatti Ekambaram ,  Srikathyayani Srikanteswara ,  Jessica C. McCarthy ,  Eve M. Schooler ,  Sebastian Schoenberg ,  Rath Vannithamby ,  Moreno Ambrosin ,  Maruti Gupta Hyde

IPC: H04W28/06 ,  H04W4/40 ,  H04W4/38 ,  H04W4/08 ,  G08G1/01 ,  H04L29/06 ,  H04N21/00 ,  H04W4/44 ,  H04L29/08 ,  G06F16/00 ,  H04W4/02

Abstract: System and techniques for publisher control in an information centric network (ICN) are described herein. Named data criteria to identify data for a workload may be constructed. A discriminator for potential publishers of the data may be constructed. An interest packet may be transmitted based on the named data criteria and the discriminator and a response to the interest packet received from one of the potential publishers.

公开(公告)号：US10939331B2

公开(公告)日：2021-03-02

申请号：US16370098

申请日：2019-03-29

Applicant: Intel Corporation

Inventor： Klaus Schneider ,  Srikathyayani Srikanteswara ,  Maruti Gupta Hyde ,  Ravikumar Balakrishnan ,  Gabriel Arrobo Vidal

IPC: H04W36/00 ,  H04W36/12 ,  H04W36/22 ,  H04W36/30 ,  H04W40/12 ,  H04L12/707 ,  H04W36/02

Abstract: Systems and techniques for information centric network (ICN) heterogeneous wireless switching are described herein. A handover event, that includes an indication for a device to switch from a first wireless link to a second wireless link, may be detected. A forwarding interest base (FIB) table may be modified to route interest packets to the second wireless link. Although the device has switched to route new out-going interest packet to the second wireless link, the device accepts data packets on both the first wireless link and the second wireless link.

公开(公告)号：US10813061B2

公开(公告)日：2020-10-20

申请号：US16134400

申请日：2018-09-18

Applicant: Intel Corporation

Inventor： Juan Fang ,  Laurent Cariou ,  Shahrnaz Azizi ,  Alexander W. Min ,  Thomas J. Kenney ,  Rath Vannithamby ,  Ravikumar Balakrishnan

IPC: H04W52/36 ,  H04W52/24 ,  H04W72/04 ,  H04W74/00 ,  H04B17/318 ,  H04L29/12 ,  H04W84/12 ,  H04W88/08 ,  H04W74/08

Abstract: Methods, apparatuses, and computer readable media for power reduction in a wireless network are disclosed. An apparatus of a first access point is disclosed comprising processing circuitry configure to decode a first PPDU, the first PPDU including a trigger for control (TOC) frame, the TOC frame comprising resource allocations for deferral transmissions, the TOC frame including a first duration field indicating a duration of a transmission opportunity (TXOP). The processing circuitry may be further configured to respond to a determination that the TOC frame includes a resource allocation by encoding a second PPDU including a preamble portion and a media access control (MAC) portion including a receive with condition (ARC) frame, the ARC frame including a second duration field indicating a remaining duration of the TXOP, an address field indicating a MAC address of the first AP, and a condition field indicating a condition.

公开(公告)号：US12021720B2

公开(公告)日：2024-06-25

申请号：US16937267

申请日：2020-07-23

Applicant: Intel Corporation

Inventor： Ajay Gupta ,  Ravikumar Balakrishnan ,  Shahrnaz Azizi ,  Maruti Gupta Hyde ,  Ariela Zeira ,  Arjun Anand ,  Jacob Winick

IPC: H04L43/0852 ,  G06F1/3203 ,  H04L47/10 ,  H04L47/50

CPC classification number: H04L43/0852 ,  G06F1/3203 ,  H04L47/10 ,  H04L47/50

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed that generate dynamic latency values. An example apparatus includes an active status controller to determine that a modem is active based on a number of packets obtained from a network, a prediction controller to predict that the number of packets are indicative of a workload type based on a trained model, and a latency value generator to generate a latency value based on the workload type of the number of packets, the latency value to cause a processor processing the number of packets to enter a power saving state or a power executing state.

公开(公告)号：US20230068386A1

公开(公告)日：2023-03-02

申请号：US17790950

申请日：2020-12-26

Applicant: Intel Corporation

Inventor： Mustafa Riza Akdeniz ,  Arjun Anand ,  Nageen Himayat ,  Amir S. Avestimehr ,  Ravikumar Balakrishnan ,  Prashant Bhardwaj ,  Jeongsik Choi ,  Yang-Seok Choi ,  Sagar Dhakal ,  Brandon Gary Edwards ,  Saurav Prakash ,  Amit Solomon ,  Shilpa Talwar ,  Yair Eliyahu Yona

IPC: G06N20/00

Abstract: The apparatus of an edge computing node, a system, a method and a machine-readable medium. The apparatus includes a processor to perform rounds of federated machine learning training including: processing client reports from a plurality of clients of the edge computing network; selecting a candidate set of clients from the plurality of clients for an epoch of the federated machine learning training; causing a global model to be sent to the candidate set of clients; and performing the federated machine learning training on the candidate set of clients. The processor may perform rounds of federated machine learning training including: obtaining coded training data from each of the selected clients; and performing machine learning training on the coded training data.

公开(公告)号：US11438104B2

公开(公告)日：2022-09-06

申请号：US16729137

申请日：2019-12-27

Applicant: Intel Corporation

Inventor： Laurent Cariou ,  Xiaogang Chen ,  Po-Kai Huang ,  Javier Perez-Ramirez ,  Shahrnaz Azizi ,  Ravikumar Balakrishnan ,  Daniel Bravo ,  Feng Jiang ,  Thomas J. Kenney ,  Qinghua Li ,  Robert Stacey

IPC: H04L1/18 ,  H04W80/02 ,  H04L1/16 ,  H04W84/12

Abstract: This disclosure describes systems, methods, and devices related to extremely high throughput (EHT) multiuser hybrid automatic repeat request (HARQ). A device may determine one or more medium access control (MAC) protocol data unit (MPDUs) to be sent to a first station device of one or more station devices, wherein the one or more MAC protocol data units (MPDUs) comprise a first MPDU. The device may segment the first MPDU into a plurality of segments, wherein the one or more segments include a first segment and a second segment. The device may cause to send the plurality of segments to the first station device. The device may identify a feedback frame received from the first station device, wherein the feedback frame comprises error information associated with the plurality of segments. The device may cause to retransmit at least one of the plurality of segments based on the error information.

公开(公告)号：US11197042B2

公开(公告)日：2021-12-07

申请号：US15849136

申请日：2017-12-20

Applicant: Intel Corporation

Inventor： Ravikumar Balakrishnan ,  Venkatesan Nallampatti Ekambaram

IPC: H04N21/236 ,  H04N5/247 ,  G08G1/16 ,  H04N21/2187 ,  H04N21/218 ,  H04N21/2743 ,  H04N21/414 ,  H04N13/194

Abstract: An embodiment of a semiconductor package apparatus may include technology to request video information from a source outside of a vehicle, receive the video information in response to the request, and construct 3D video information for the vehicle based on the received video information. Other embodiments are disclosed and claimed.