ML Configuration Framework for Wireless Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current wireless communication systems face challenges in effectively integrating machine learning (ML) and artificial intelligence (AI) techniques to enhance system performance, particularly in 5G and beyond networks, due to limitations in configuring and managing ML/AI approaches, model parameters, and UE capabilities across different components.
Innovation Solution
The proposed solution involves a framework for configuring ML/AI approaches in wireless communication systems, including the transmission of configuration information from base stations to user equipment (UEs) for enabling/disabling ML operations, selecting ML models, and updating model parameters, with assistance information generated based on local data and UE capabilities, allowing for inference operations to be performed at either the UE or the base station.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If ML/AI techniques are integrated to enhance system performance, then system performance is improved, but device complexity increases
Solution Approach 1:
The patent segments the ML/AI system into multiple components: base station configuration module, UE capability reporting module, model parameter transmission module, and inference execution module. This segmentation allows complex ML/AI functionality to be distributed across network elements, managing overall system complexity while maintaining performance benefits.
Solution Approach 2:
The patent introduces configuration information as an intermediary mechanism that mediates between the base station's ML model parameters and the UE's inference operations. This intermediary layer standardizes the interaction interface, managing complexity by providing a structured communication protocol between network elements.
2Adaptability or versatility
If configuration information is transmitted from base station to UE, then ML model adaptability is improved, but loss of information increases
Solution Approach 1:
The patent applies preliminary action by having the base station transmit configuration information containing ML model parameters to the UE in advance, before the UE needs to perform inference operations. This advance provisioning ensures that the UE has the necessary model parameters available locally, preventing information loss during real-time operations and enabling rapid adaptation to changing network conditions.
3Speed
If assistance information is generated based on local data, then processing speed is improved, but measurement precision decreases
Solution Approach 1:
The patent implements feedback mechanisms where the UE reports capability information and assistance information back to the base station. This feedback loop allows the base station to refine its configuration information and ML model parameters based on actual UE performance and network conditions, progressively improving measurement precision while maintaining the speed benefits of local processing.
Data Source
AI summary
ML/AI configuration information transmitted from a base station to a UE includes one or more of enabling/disabling an ML approach for one or more operations, one or more ML models to be used for the one or more operations, trained model parameters for the one or more ML models, and whether ML model parameters received from the UE at the base station will be used. Assistance information generated based on the configuration information is transmitted from the UE to the base station. The UE may perform an inference regarding operations based on the configuration information and local data, or the inference may be performed at one of the base station or another network entity based on assistance information received from UEs including the UE. The assistance information may be local data such as UE location, UE trajectory, or estimated DL channel status, inference results, or updated model parameters.