Multi-criteria reinforcement learning-based admission control in private networks

The reinforcement learning-based admission control system dynamically manages admission requests in private 5G networks by optimizing network load parameters and key performance indicators, addressing the challenges of asymmetric and aperiodic traffic patterns and improving performance indicators.

WO2024237943A1PCT designated stage expired Publication Date: 2024-11-21DELL PROD LP
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
PCT/US2023/036183
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-12
Filing Date
2023-10-28
Publication Date
2024-11-21

AI Technical Summary

Technical Problem

Existing admission control frameworks in private 5G networks fail to maintain key performance indicators due to asymmetric and aperiodic traffic patterns, leading to unpredictable traffic load metrics and inability to satisfy performance expectations of user entities.

Method used

A reinforcement learning-based system for admission control that uses reward functions to dynamically manage admission requests on a per-quality of service flow basis, optimizing network load parameters and key performance indicators, allowing for dynamic and adaptive decision-making in response to changing network conditions and user entity permissions.

Benefits of technology

This approach enables dynamic optimization of admission control decisions, improving key performance indicators and achieving higher rewards on a per-QoS and per-UE basis, effectively addressing the challenges of asymmetric and aperiodic traffic patterns in private 5G networks.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure US2023036183_21112024_PF_FP_ABST
    Figure US2023036183_21112024_PF_FP_ABST
Patent Text Reader

Abstract

Technology described herein can comprise a system comprising a processor and a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising requesting, via a prediction process executed by the system, a subscription to a quality of service flow of a private network, based on a key performance indicator report received from a node of the private network, defining, via the prediction process, a reward function that determines a quantified reward based on a level of satisfaction corresponding to at least one key performance indicator for the node, and based on the reward function, identifying, via a decision process executed by the system, an action, corresponding to a predicted threshold for the level of satisfaction of the at least one key performance indicator, to be performed to respond to a request for admission to the private network from a user equipment.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Multi-Criteria Reinforcement Learning-Based Admission Control in Private Networks

    US20240380671A1

  • Network configuration optimization using a reinforcement learning agent

    US20220231912A1