RAN ML Capability Signaling for Wireless Device Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
There is currently no framework within 3GPP to support the use of Machine Learning (ML) models in Radio Access Network (RAN) operations at wireless devices, posing challenges for integrating ML into existing communication networks.
Innovation Solution
A framework is provided for managing wireless devices by first and second RAN nodes to facilitate the use and execution of ML models, involving the exchange of information between RAN nodes regarding the capability and configuration of ML models at wireless devices, enabling optimized RAN operations such as handover, beam management, and traffic prediction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If ML models are integrated into RAN operations at wireless devices, then system performance and network efficiency are improved, but device complexity and integration challenges increase
Solution Approach 1:
The patent introduces a framework with intermediary components including an ML model manager at the RAN node and capability indication mechanisms that mediate between the ML model execution at wireless devices and the RAN operations. This intermediary layer manages the complexity of ML integration by handling model deployment, capability assessment, and coordination between network nodes and devices, thereby improving network efficiency while controlling integration complexity.
2Adaptability or versatility
If information exchange between RAN nodes regarding ML model capability is implemented, then interoperability and informed management are improved, but signaling overhead increases
Solution Approach 1:
The patent extracts ML model capability information as a separate, dedicated indication that is transmitted between RAN nodes. By taking out this specific capability information from general device descriptions and handling it as a distinct element in the information exchange, the framework enables targeted interoperability support while minimizing unnecessary signaling overhead. The capability indication is integrated into existing RAN procedures rather than creating separate extensive signaling protocols.
Data Source
AI summary
A method is disclosed for managing a wireless device that is operable to connect to a communication network. The communication network comprises a Radio Access Network (RAN), and the method is performed by a first RAN node of the communication network. The method comprises receiving, from a second RAN node in the communication network, information indicating whether a wireless device is capable of executing a Machine Learning (ML) model that is operable to provide an output on the basis of which at least one RAN operation performed by the wireless device may be configured.