公开(公告)号：US12096248B2

公开(公告)日：2024-09-17

申请号：US17662053

申请日：2022-05-04

Applicant: Tata Consultancy Services Limited

Inventor： Garima Mishra ,  Nikita Trivedi ,  Hemant Kumar Rath ,  Bighnaraj Panigrahi ,  Shameemraj Nadaf

IPC: H04W24/02 ,  H04B1/715 ,  H04W16/14 ,  H04W72/541 ,  H04W84/12

CPC classification number: H04W24/02 ,  H04B1/715 ,  H04W16/14 ,  H04W72/541 ,  H04W84/12

Abstract: This disclosure relates to method and system for improving Wi-Fi performance in co-existing communication networks using learning methodologies. In recent times, most of telecom operators have expressed interest in deploying LTE (Long-Term Evolution) over the unlicensed spectrum. However, simultaneous use of unlicensed band (by operators using LTE and other Wi-Fi) presents coexistence challenges in terms of network performance especially for the Wi-Fi. The disclosed techniques enable improving the Wi-Fi performance in the co-existing communication networks based on learning methodologies. The disclosed techniques improve Wi-Fi performance based on several steps that includes detecting an interfering channel, and further identifying an optimal channel to mitigate the interference caused by the detected interfering channel. The optimal channel is identified based on an optimization technique, wherein the optimization technique is a reinforcement learning technique based on a Q-learning.

公开(公告)号：US12101637B2

公开(公告)日：2024-09-24

申请号：US17672991

申请日：2022-02-16

Applicant: Tata Consultancy Services Limited

Inventor： Bighnaraj Panigrahi ,  Sumanta Patro ,  Hemant Kumar Rath ,  Shameemraj Nadaf ,  Garima Mishra

IPC: H04W16/10 ,  H04W16/04 ,  H04W24/08

CPC classification number: H04W16/10 ,  H04W16/04 ,  H04W24/08

Abstract: Fifth generation and beyond (5G+) systems are expected to adopt new network architectures, services, and deployment schemes for compatibility with the latest technologies and end user's needs. With increase in user equipment (UE), also come variety of advanced applications and use-cases, wherein each application type has its own KPI requirements. Existing resource allocation schemes in cellular networks are not able to handle such dynamic requirements due to which network slice can lead to unwanted mismanagement of resources. Present application provides systems and methods for application-aware dynamic slicing in radio access network (RAN), wherein RAN slicing is proactively managed by learning historical slice demands and consumptions. Once slices are created, the system allocates resources to user equipment by following optimal inter-slice and intra-slice mechanisms based on application type(s), traffic demand(s) and wireless characteristics of UE. Upon resource allocation the UE are further monitored to avoid resource misutilization and resource wastage.