Communication control system and communication control method
The communication control system enhances learning efficiency and inference accuracy in RANs by using a distributed control architecture with Non-RT and Near-RT RICs to associate learned models with user terminals based on radio environment classifications.
JP2025138423APending Publication Date: 2025-09-25KDDI CORP
0 Cites 0 Cited by
Patent Information
- Application Number
- JP2024037514
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-03-11
- Publication Date
- 2025-09-25
AI Technical Summary
Technical Problem
Distributed reinforcement learning in RAN control results in reduced model size or training data, leading to inadequate learning of diverse radio environments for user equipment, affecting inference accuracy.
Method used
A communication control system with a first control unit (Non-RT RIC) for learning and a second control unit (Near-RT RIC) for inference, utilizing model association information to associate learned models with user terminals based on radio environment classifications, and an interface for message transmission between the units.
Benefits of technology
Improves learning efficiency and inference accuracy of radio access networks by adapting models to specific user environments.
✦ Generated by Eureka AI based on patent content.
Abstract
To improve the learning efficiency of models and the inference accuracy of trained models in the control of a radio access network.SOLUTION: A communication control system includes a first control unit that performs learning to infer predetermined communication control items for models provided corresponding to respective classifications of radio environments around a user terminal, in a radio access network in accordance with O-RAN specifications, and a second control unit that uses a model trained by the first control unit for the user terminal associated with the classification of the radio environment corresponding to the trained model. The first control unit transmits model association information to the second control unit for associating each trained model of the classification of the radio environment with the user terminal, and the second control unit receives the model association information transmitted from the first control unit.SELECTED DRAWING: Figure 5
Need to check novelty before this filing date? Find Prior Art