公开(公告)号：WO2021230712A1

公开(公告)日：2021-11-18

申请号：PCT/KR2021/006086

申请日：2021-05-14

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： AGARWAL, Rishav ,  KARJEE, Jyotirmoy ,  EDA, Raja Moses Manoj Kumar ,  GUHA, Shouvik

IPC: H04W36/00 ,  H04W36/02 ,  H04W28/02 ,  H04W72/14

Abstract: Disclosed herein is related to dual connectivity configuration, that discloses methods and systems for managing a handover, which may include managing throughput loss occurring before/after/during handovers in a dual connectivity configuration. One solution performed before handover includes managing throughput loss by temporarily boosting Buffer Status Report (BSR) of a stack not undergoing handover and transmitting all data packets using the Uplink resource grant received for the boosted BSR. Another solution performed after handover includes determining split ratio before handover itself based on nature and bandwidth information of target cell, and applying it after the handover, to mitigate throughput loss that occurs after handover. Another solution performed during handover is a combination of first solution of boosting BSR and second solution of determining split ratio. Another solution enables prediction of split ratio of potential target cells for an estimated handover using an artificial intelligence model.

公开(公告)号：WO2022203400A1

公开(公告)日：2022-09-29

申请号：PCT/KR2022/004085

申请日：2022-03-23

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： KARJEE, Jyotirmoy ,  ANAND, Kartik ,  BHARGAV, Vanamala Narasimha ,  S, Praveen Naik ,  DABBIRU, Ramesh Babu Venkat ,  N, Srinidhi ,  NIGAM, Anshuman ,  JHA, Rishabh Raj

IPC: H04L67/60 ,  H04L67/12 ,  H04L67/289 ,  H04L67/133 ,  G06N3/02

Abstract: A method and device for execution of deep neural network (DNN) in an internet of things (IoT) edge network are provided. In an embodiment, at least one edge device within communication range of an IoT device are selected. Further, a network for connecting the IoT device with the at least one selected edge device is identified. A split ratio is determined based on an inference time of the DNN and a transmission time required for transmitting output of each layer of DNN from the IoT device to the selected at least one edge device. Finally, a plurality of layers of the DNN are split into a first part and a second part based on the split ratio, and the second part is transmitted to the selected at least one edge device through the identified network. The first part is executed on the IoT device, and the second part is executed on the selected at least one edge device.

公开(公告)号：WO2023085819A1

公开(公告)日：2023-05-19

申请号：PCT/KR2022/017670

申请日：2022-11-10

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： CHAKRABORTY, Prasenjit ,  THURLAPATI, Narasimha Rao ,  N, Srinidhi ,  YIP, Eric Ho Ching ,  KARJEE, Jyotirmoy ,  KAINTH, Jaskamal ,  VENKAT DABBIRU, Ramesh Babu

IPC: G06N3/08 ,  G06N20/00

Abstract: Provided is a method for adaptively streaming an artificial intelligence (AI) model file, including determining a capability of a first electronic device and a capability of a second electronic device, network information associated with the first and second electronic devices, and AI model information associated with the AI model file; determining to adaptively stream the AI model file based on the determined capabilities and information; pre-processing the AI model file; and adaptively streaming the AI model.

公开(公告)号：WO2023287211A1

公开(公告)日：2023-01-19

申请号：PCT/KR2022/010259

申请日：2022-07-14

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： GANDIKOTA, Jagadeesh ,  HASHMI, Danish Ehsan ,  KARJEE, Jyotirmoy ,  POONIYA, Ankur

IPC: H04W48/18 ,  H04W76/10 ,  H04W28/02

Abstract: A method, implemented in a User Equipment (UE), of selecting network slices for servicing application requests is disclosed. The method comprises receiving an application request from an application for establishing a new protocol data unit (PDU) session with a network over a first network slice. The application request defining one or more PDU session requirements. The method further includes identifying a plurality of network slices other than the first network slice based on the one or more PDU session requirements defined in the application request. Further, the method includes, selecting a second network slice from the plurality of network slices based on a UE Route Selection Policy (URSP) configuration defined by the network for the UE. Furthermore, the method includes servicing the application request using the second network slice.