PUCCH Resource Allocation for AI-Based Uplink Control Priority
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current 3GPP specifications lack mechanisms to support the interpretation and prioritization of uplink control information (UCI) generated by AI/ML models in wireless communication networks, leading to undefined bit buckets and challenges in transmitting AI/ML model parameters and outputs.
Innovation Solution
Configuring PUCCH resource sets and implementing UE procedures for multiplexing and collision handling to transmit bit buckets generated by AI/ML models, with differentiated priority and reliability handling for AI/ML model outputs and legacy UCI types.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If AI/ML models are deployed at UE to generate uplink control information, then channel prediction accuracy and positioning accuracy are improved, but the 3GPP specifications lack mechanisms to support interpretation and prioritization of AI-generated UCI, leading to undefined bit buckets and transmission challenges
Solution Approach 1:
The patent segments AI-generated UCI into distinct types (e.g., channel state information, positioning information, beam management information) with different priority levels and interpretation requirements. This segmentation allows the system to handle diverse AI model outputs through standardized, type-specific procedures rather than requiring a single complex interpretation mechanism for all AI-generated data.
Solution Approach 2:
The patent introduces an intermediary layer of standardized UCI formatting and priority tagging that sits between the AI/ML model output and the existing 3GPP specification processing. This intermediary structure translates diverse AI model outputs into standardized formats that can be interpreted by existing network infrastructure, bridging the gap between AI-generated data and traditional communication protocols.
2Loss of information
If multiple UCI types including AI-generated bit buckets are transmitted on PUCCH, then information completeness is improved, but resource allocation and collision handling become more complex
Solution Approach 1:
The patent implements dynamic resource allocation mechanisms where PUCCH resources are adaptively assigned based on the priority, size, and type of UCI being transmitted. The system can dynamically adjust resource allocation in response to varying AI model output requirements, allowing high-priority AI-generated information to receive adequate resources while maintaining efficient utilization for legacy UCI types.
Solution Approach 2:
The patent changes key parameters of PUCCH transmission including resource block allocation, modulation and coding schemes, and priority levels based on the specific type and importance of UCI content. By adjusting these transmission parameters dynamically according to UCI category, the system achieves complete information transmission without requiring fixed, overly complex resource allocation structures.
3Reliability
If differentiated priority handling is implemented for AI/ML model outputs and legacy UCI, then transmission reliability is improved, but the complexity of UE procedures for multiplexing and collision handling increases
Solution Approach 1:
The patent applies preliminary action by pre-configuring priority levels, resource allocations, and collision resolution rules for different UCI types before transmission occurs. The UE is provided with standardized procedures and lookup tables that define how to handle various UCI combinations, eliminating the need for complex real-time decision-making during transmission and simplifying the operational complexity while maintaining reliability.
4Reliability
If PUCCH resources are allocated for AI/ML model parameters and outputs, then AI/ML model performance is improved, but radio resource utilization efficiency may be reduced without proper multiplexing mechanisms
Solution Approach 1:
The patent creates universal PUCCH resource structures that can serve multiple functions - transmitting both traditional legacy UCI (HARQ-ACK, CSI, SR) and AI-generated UCI (channel predictions, positioning information, beam management data) through the same physical channel. This multi-functionality allows the system to support AI/ML model performance requirements while maintaining efficient radio resource utilization by avoiding dedicated separate channels for AI data.
Data Source
AI summary
According to some embodiments, a method performed by a wireless device comprises obtaining a priority associated with each of one or more fields of an uplink transmission. An interpretation of the one or more fields is based on a machine learning model and is undefined with respect to an existing uplink control information (UCI) type. The method further comprises allocating physical uplink control channel (PUCCH) resources for one of the one or more fields based on the obtained priority and transmitting the uplink transmission using the allocated PUCCH resources.