公开(公告)号：US20240088952A1

公开(公告)日：2024-03-14

申请号：US18458605

申请日：2023-08-30

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Seung Eun HONG ,  Jun Beom KIM ,  Seok Hwan PARK ,  Hoon LEE

IPC: H04B7/0426 ,  H04B17/391

CPC classification number: H04B7/043 ,  H04B17/3913

Abstract: The present disclosure discloses beamforming methods and apparatuses. According to an exemplary embodiment of the present disclosure, an antenna message generation deep neural network (DNN) and a beam characteristic generation DNN of a bipartite graph neural network (BGNN) having terminals as vertices on one side and APs as vertices on another side may be constructed.

公开(公告)号：US20240297685A1

公开(公告)日：2024-09-05

申请号：US18594545

申请日：2024-03-04

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Seung Eun HONG ,  Seok Hwan PARK ,  Dae Sung YU ,  Hoon LEE

IPC: H04B7/0426 ,  H04B7/024 ,  H04W52/24 ,  H04W52/28 ,  H04W52/40

CPC classification number: H04B7/0426 ,  H04B7/024 ,  H04W52/242 ,  H04W52/282 ,  H04W52/40

Abstract: A method for power allocation in a dAP may comprise: when a change cycle of a transmit power determination vector arrives, generating an uplink message including long-term CSI, the uplink message being normalized such that the long-term local CSI becomes a value within a preconfigured limit range; transmitting the uplink message to a central processing unit through a fronthaul; receiving a downlink message vector for power allocation from the central processing unit through the fronthaul; generating decentralized determination information using the downlink message vector; and extracting a transmit power determination vector based on the decentralized determination information.

公开(公告)号：US20220029665A1

公开(公告)日：2022-01-27

申请号：US17380826

申请日：2021-07-20

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE ,  Pukyong National University Industry-University Cooperation Foundation

Inventor： Seung Eun HONG ,  Hoon LEE ,  Seok Hwan PARK ,  Jun Beom KIM

IPC: H04B7/0426 ,  H04B7/08 ,  G06N3/08

Abstract: Disclosed is a beamforming method using a deep neural network. The deep neural network may include an input layer, L hidden layers, and an output layer, and the beamforming method may include: obtaining channel information h between a base station and K terminals and a transmit power limit value P of the base station, and inputting h and P into the input layer; and performing beamforming on signals to be transmitted to the K terminals using beamforming vectors derived using the output layer and at least one activation function, wherein the base station transmits the signals to the K terminals using M transmit antennas. Here, the output layer may be configured in a direct beamforming learning (DBL) scheme, a feature learning (FL) scheme, or a simplified feature learning (SFL) scheme.