公开(公告)号：US20210143933A1

公开(公告)日：2021-05-13

申请号：US17082713

申请日：2020-10-28

Applicant: Nokia Solutions and Networks Oy

Inventor： Prasanna KAMAGANAHALLI MUDLAPPA ,  Joseph THALIATH ,  Vaibhav SINGH

IPC: H04L1/00 ,  H04B7/0413 ,  G06N20/00 ,  H04W72/12

Abstract: An apparatus, method and computer program is described comprising: executing, in a first mode of operation, a MIMO for one or more user devices eligible to transmit data in a slot of a packet scheduler, to generate MIMO operation outputs; obtaining, in a second mode of operation, estimated MIMO operation outputs for said one or more user devices from a lookup table; and determining whether to operate in the first mode of operation or the second mode operation.

公开(公告)号：US20240152820A1

公开(公告)日：2024-05-09

申请号：US18548509

申请日：2021-03-23

Applicant: Nokia Solutions and Networks Oy

Inventor： Vaibhav SINGH ,  Anand BEDEKAR ,  Shivanand KADADI ,  Parijat BHATTACHARJEE

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: An apparatus includes circuitry configured to: receive a request from a radio access network algorithm to determine whether there is a distribution shift related to a temporal characteristic of a cell of a communication network; request data from a radio access network node or a controller platform related to the temporal characteristic; receive the requested data related to the cell from the radio access network node or the controller platform; determine whether there is a distribution shift related to the temporal characteristic; in response to determining that there is a distribution shift, select a learning type for an update to a model; and update the model such that, when the model is provided to an inference server, causes the radio access network algorithm to use the updated model to perform at least one action to optimize the performance of the radio access network node or other radio access network node.

公开(公告)号：US20230135872A1

公开(公告)日：2023-05-04

申请号：US17976376

申请日：2022-10-28

Applicant: NOKIA SOLUTIONS AND NETWORKS OY

Inventor： Vaibhav SINGH ,  Anand BEDEKAR ,  Jun HE

IPC: H04W52/02 ,  H04W24/10

Abstract: To maximize power saving in a radio access network comprising cells, an optimal action amongst actions comprising switching on one or more cells, switching off one or more cells, and doing nothing is determined using a trained model, which maximizes a long term reward on tradeoff between throughput and power, the trained model taking as input a load estimate. The trained model may be updated online using measurement results on load, throughput and power consumption.

公开(公告)号：US20250081010A1

公开(公告)日：2025-03-06

申请号：US18728194

申请日：2022-01-14

Applicant: Nokia Solutions and Networks Oy

Inventor： Anand BEDEKAR ,  Vaibhav SINGH ,  Shivanand KADADI ,  Claudiu MIHAILESCU ,  Dora BOVIZ ,  Jun HE

IPC: H04W24/08 ,  H04W24/02

Abstract: Systems, methods, and software for a Radio Access Network (RAN). In one embodiment, a system identifies a plurality of cells within the RAN, and groups the cells into cell groups. The system performs a training process to train group Machine-Learning (ML) models for the cell groups based on training data for the cell groups, and evaluates a performance of the group ML models for the cell groups based on evaluation data for the cell groups. The system provides the group ML models for the cell groups to a RAN management system or the like when the performance of the group ML models satisfies a performance threshold.

公开(公告)号：US20240129941A1

公开(公告)日：2024-04-18

申请号：US18546891

申请日：2021-04-06

Applicant: Nokia Solutions and Networks Oy

Inventor： Vaibhav SINGH ,  Prasanna MUDLAPPA

IPC: H04W72/52 ,  H04W48/20 ,  H04W72/21 ,  H04W72/51 ,  H04W72/566

CPC classification number: H04W72/52 ,  H04W48/20 ,  H04W72/21 ,  H04W72/51 ,  H04W72/566

Abstract: There are provided measures for efficient cell baseband processing pooling. Such measures exemplarily comprise acquiring a predicted future computational load of baseband processing for each selected radio cell of a plurality of radio cells, and determining an allocation of each selected radio cell of said plurality of radio cells to anyone of a plurality of processing resource units based on said predicted future computational load of baseband processing for each selected radio cell of said plurality of radio cells and computation capabilities of each of said plurality of processing resource units.

公开(公告)号：US20210345233A1

公开(公告)日：2021-11-04

申请号：US17274652

申请日：2019-08-29

Applicant: NOKIA SOLUTIONS AND NETWORKS OY

Inventor： Vaibhav SINGH ,  Parijat TACHARJEE

IPC: H04W48/16 ,  H04W48/20 ,  H04W24/02

Abstract: Systems, methods, apparatuses, and computer program products for dynamic target cell selection for application of RAN optimization are provided. One method includes receiving a request, from one or more radio access network optimization services, that comprises a list of attributes corresponding to characteristics of a cell and a cell selection criterion for each of the attributes, receiving, from one or more radio access network cells, a data stream comprising metrics for at least one of the cell or users in the cell. The method may also include generating, based on the received request and the metrics, a list of zero or more cells that meet the selection criterion for one of the radio access network optimization services or for a group of the radio access network optimization services, and sending, to a respective one of said one or more radio access network optimization services, the generated list of said zero or more cells that meets the selection criterion for the respective one or more radio access network optimization services.

公开(公告)号：US20230319707A1

公开(公告)日：2023-10-05

申请号：US18205053

申请日：2023-06-02

Applicant: NOKIA SOLUTIONS AND NETWORKS OY

Inventor： Vaibhav SINGH ,  Anand BEDEKAR ,  Jun HE

IPC: H04W52/02 ,  H04W24/10

CPC classification number: H04W52/0206 ,  H04W24/10

Abstract: To maximize power saving in a radio access network comprising cells, an optimal action amongst actions comprising switching on one or more cells, switching off one or more cells, and doing nothing is determined using a trained model, which maximizes a long term reward on tradeoff between throughput and power, the trained model taking as input a load estimate. The trained model may be updated online using measurement results on load, throughput and power consumption.