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.
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
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.
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.
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.
Smart Images

Figure US2023036183_21112024_PF_FP_ABST
Abstract
Citation Information
Patent Citations
Multi-Criteria Reinforcement Learning-Based Admission Control in Private Networks
US20240380671A1
Network configuration optimization using a reinforcement learning agent
US20220231912A1
