R1-2410587
discussion
On Associated ID for Beam Management Use Case
From NTU
Summary
NTU proposes a collaborative approach for AI/ML-based beam management to address codebook mismatch issues between UE prediction models and network implementations. The document contains 2 main proposals focusing on relaxing 'similar properties' requirements for associated IDs and enabling dual reporting of predicted and measured beams.
Position
NTU advocates FOR a collaborative UE-network approach using standardized codebooks (like RAN4 testing codebooks) to reduce UE implementation complexity, opposing the current associated ID approach which requires UEs to support multiple AI/ML models for different vendor codebooks. They push AGAINST revealing proprietary vendor algorithms through codebook switching indications.
Key proposals
- Proposal 1 (Discussion): UE may assume similar properties of DL Tx beams with same associated ID, with 'similar properties' defined from UE CSI report generation and base station processing perspective, allowing BS to use different beam properties than indicated as long as reports are processed correctly
- Proposal 2 (Discussion): Network should be allowed to request UE reporting both the best beam based on its prediction and a subset of measured beams to enable BS side model to correct codebook mismatch through collaborative approach