-
公开(公告)号:US20200296569A1
公开(公告)日:2020-09-17
申请号:US16813146
申请日:2020-03-09
Applicant: Samsung Electronics Co., Ltd.
Inventor: Satish KUMAR , Sukhdeep SINGH , Suman KUMAR , Avinash BHAT , Rahul BANERJI , Naman GUPTA , Seungil YOON
Abstract: A method and Network function for controlling an operation of a device based on a service provided to the device is provided. The method includes obtaining at least one of information about the service requested by the device, movement information of the device, or capability information of the device, determining a characteristic of the service provided to the device based on at least one of the information about the service, the movement information of the device, or the capability information of the device, generating service setting information for the service provided to the device based on the determined characteristic of the service, and transmitting, to an Access and Mobility Function (AMF), the service setting information.
-
公开(公告)号:US20250106311A1
公开(公告)日:2025-03-27
申请号:US18971931
申请日:2024-12-06
Applicant: Samsung Electronics Co., Ltd.
Inventor: Sukhdeep SINGH , Madhan Raj KANAGARATHINAM , Avinash BHAT
IPC: H04L69/164 , H04L41/16 , H04L65/80
Abstract: Embodiments of the disclosure disclose a method and a network node for selecting QUIC streams in wireless communication. As such, current values associated with network parameters related to a data session in real-time are received by network node in a wireless communication system. The network parameters include at least one of: connection metrics, network condition and a type of service. As such, new values of the network parameters for the data session are predicted by the network node using an artificial intelligence (AI) model based on the current values. A plurality of QUIC streams related to the data session are determined based on new network parameters. Each QUIC stream of the plurality of QUIC streams is selected from at least: reliable QUIC stream, semi-reliable QUIC stream, and unreliable QUIC stream. The plurality of QUIC streams are streamed in the wireless communication system.
-
公开(公告)号:US20240314585A1
公开(公告)日:2024-09-19
申请号:US18427189
申请日:2024-01-30
Applicant: Samsung Electronics Co., Ltd.
Inventor: Joseph THALIATH , Jaijin LIM , Seungil YOON , Sukhdeep SINGH , Sandeep Kumar JAISAWAL
Abstract: Various embodiments herein achieve method for optimizing a performance of a customer premises equipment (CPE) in a wireless network by a network apparatus. The method includes receiving a measurement information from at least one CPE. Further, the method includes receiving a measurement information from at least one RAN node. Further, the method includes detecting whether a performance associated with at least one CPE is degraded based on the received measurement information from the at least one CPE. Further, the method includes identifying a RAN UE ID for the at least one CPE whose performance is degraded by correlating the measurement information received from the at least one CPE and the measurement information received from the at least one RAN node. Further, the method includes applying an action based on the identified RAN UE ID.
-
公开(公告)号:US20240223458A1
公开(公告)日:2024-07-04
申请号:US18497319
申请日:2023-10-30
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Sukhdeep SINGH , Joseph Thaliath , Sandeep Kumar Jaisawal , Seungil Yoon , Ashish Jain , Avinash Bhat , Ganesh Kumar Thangavel
IPC: H04L41/12 , H04L41/14 , H04L41/16 , H04L41/5009
CPC classification number: H04L41/12 , H04L41/145 , H04L41/16 , H04L41/5016
Abstract: Embodiments herein disclose a method and network apparatus for network performance evaluation using AI-based network cloning. The method includes constructing one or more AI-based network clones of one or more network nodes. The one or more AI-based network clones mimics a data pattern and cell behavior of the one or more network nodes. Further, the method includes receiving a solution predicted by an AI server to mitigate one or more problems associated with one or more services of the one or more network nodes. Further, the method includes evaluating a performance of the one or more AI-based network clones by deploying the solution on the one or more AI-based network clones. Further, the method includes sending the solution to the one or more network nodes for deployment or retraining based on the performance of the one or more AI-based network clones.
-
公开(公告)号:US20240048640A1
公开(公告)日:2024-02-08
申请号:US18380980
申请日:2023-10-17
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Sukhdeep SINGH , Madhan Raj KANAGARATHINAM
CPC classification number: H04L67/62 , H04L12/1881 , H04L12/185
Abstract: A method managing multipath communication includes acquiring a plurality of network addresses respectively corresponding to a plurality of servers associated with a domain, sending a data request to at least one server of the plurality of servers based on the acquired plurality of network addresses, receiving a first data packet transmitted from a first server of the plurality of servers in response to the data request, the first data packet being received first in order among a plurality of data packets received from the plurality of servers in response to the data request, accepting the first data packet, and rejecting data packets transmitted from each server of the plurality of servers other than the first server.
-
公开(公告)号:US20230031470A1
公开(公告)日:2023-02-02
申请号:US17863576
申请日:2022-07-13
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Sukhdeep SINGH , Joseph THALIATH , Vivek SAPRU , Sandeep Kumar JAISAWAL , Naman AGARWAL , Seungil YOON , Hoejoo LEE
IPC: H04L41/16 , G06N20/00 , H04L41/5006 , H04W48/18 , G06K9/62
Abstract: The embodiments herein disclose a method for managing machine learning (ML) services in a wireless communication network. The method includes: storing a plurality of ML packages, each executing a network service request; receiving a trigger based on the network service request from a server; determining a plurality of parameters corresponding to the network service request, on receiving the trigger from the server; determining an ML package based on the trigger and the plurality of parameters corresponding to the network service request; and deploying the determined at least one ML package for executing the network service request.
-
公开(公告)号:US20200382991A1
公开(公告)日:2020-12-03
申请号:US16963126
申请日:2019-01-18
Applicant: Samsung Electronics Co., Ltd.
Inventor: Madhan Raj KANAGARATHINAM , Sukhdeep SINGH , Irlanki SANDEEP , Ankur CHAUHAN , Avinash BHAT , Hongshik KIM , Sungin KIM
IPC: H04W28/02 , H04L12/801 , H04L12/807
Abstract: Accordingly the embodiments herein provide a method for dynamically controlling a TCP congestion window. The method includes estimating, by an electronic device 100, a real time available bandwidth for an available network. Further, the method includes deriving, by the electronic device 100, a dynamic congestion window control factor from the estimated real time available bandwidth. Further, the method includes modifying, by the electronic device 100, the congestion window based on the derived dynamic congestion window control factor. In an embodiment, the congestion window is modified by passing the real time available bandwidth information from a lower layer of a modem to a higher layer of a TCP Stack and adjusting the congestion window.
-
8.
公开(公告)号:US20250053868A1
公开(公告)日:2025-02-13
申请号:US18752263
申请日:2024-06-24
Applicant: Samsung Electronics Co., Ltd.
Inventor: Sandeep Kumar JAISAWAL , Sukhdeep SINGH , Joseph THALIATH , Seungil YOON , Peter Moonki HONG
IPC: G06N20/00
Abstract: Methods for optimizing training of a data driven model in a wireless network by data driven model validation controller running in electronic device. The method may include obtaining and selecting a candidate data driven model from a plurality of candidate data driven models. The method may include determining whether the selected candidate data driven model meets a predefined prediction. The method may include deploying the selected candidate data driven model to a target deployment environment upon determining that the selected candidate data driven model meets the prediction. The method may include sending the selected candidate data driven model to a data driven model optimizer running in the electronic device for tuning a hyper-parameter and the data driven technique running in the data driven model upon determining that the selected candidate data driven model does not meet the prediction.
-
公开(公告)号:US20240046151A1
公开(公告)日:2024-02-08
申请号:US18305712
申请日:2023-04-24
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Sukhdeep SINGH , Vivek SAPRU , Joseph THALIATH , Ganesh Kumar THANGAVEL , Ashish JAIN , Seungil YOON , Hoejoo LEE , Hunje YEON
IPC: G06N20/00
CPC classification number: G06N20/00
Abstract: A system and/or method for automated ML model retraining by an electronic device. The system and/or method may include one or more of: running a first ML model and a second ML model, predicting an accuracy degradation of the first ML model using the second ML model, determining whether the predicted accuracy degradation meets a pre-defined threshold, and/or retraining the first ML model when the predicted accuracy degradation meets the pre-defined threshold.
-
公开(公告)号:US20240007874A1
公开(公告)日:2024-01-04
申请号:US18348039
申请日:2023-07-06
Applicant: Samsung Electronics Co., Ltd.
Inventor: Vishal MURGAI , Swaraj KUMAR , Sukhdeep SINGH
IPC: H04W24/02
CPC classification number: H04W24/02
Abstract: Embodiments herein disclose a method and a device for embedding neural networks as a matrix for a network device in wireless networks. The method includes receiving s from the network device. Further, the method also includes determining the KPI among the plurality of KPIs as target KPIs that related to a network anomaly using a ML model. Further, the method also includes determining a correlation of the target KPI with the plurality of KPIs for the network anomaly using the ML model. Further, the method also includes determining the matrix indicating a relation of the target KPI with the plurality of KPIs. Furthermore, the method includes optimizing a resource of the network device by embedding the matrix in the network device.
-
-
-
-
-
-
-
-
-