R1-2409749
discussion
Specification support for beam management
Summary
Tejas Networks Limited submits 36 proposals and 6 observations to address open issues for AI/ML-based beam management in NR, covering both UE-sided and NW-sided models. The document focuses on ensuring consistency between training and inference via Associated IDs, optimizing reporting overhead through differential L1-RSRP and dynamic resource configuration, and defining performance monitoring metrics for Type 1 and Type 2 scenarios.
Position
Tejas Networks proposes that the Associated ID be configured within the CSI-Report Config to ensure consistency between training and inference phases for UE-sided models, mapping to both Set A and Set B resources. They support using L1 signaling for Type 1 NW-side performance monitoring while allowing higher-layer signaling for larger data volumes, and propose configuring monitoring resources within existing CSI report configurations to reduce overhead. For NW-sided models, they propose reporting differential L1-RSRP with larger quantization step sizes and supporting up to M=256 beams, utilizing bitmaps for beam identification when M < N. They argue for dynamic configuration of prediction windows and TCI state indications based on UE mobility and channel coherence time, specifically suggesting N=2 to 4 joint TCI states for BM-Case 2. Additionally, they propose that for UE-sided BM-Case 1, only Set B needs to be configured for inference reporting, simplifying the resource setup.
Key proposals
- Proposal 1 (Consistency for additional condition for UE-sided model): Associated ID should be configured as part of the CSI-Report Config and mapped to resources in Set A (predicted beams) and Set B (measured beams).
- Proposal 6 (Performance monitoring): For Type 1 performance monitoring Option 1 (NW-side), L1 signaling can be used to send measurement results to the NW for metric calculation, without precluding higher layer signaling.
- Proposal 9 (Configuration of RS for Set A and Set B for NW sided model): Support multiple resource sets associated with one L1 beam report, where Set A reports beam IDs and Set B reports L1-RSRP measurements.
- Proposal 13 (Configuration of RS for Set A and Set B for UE-sided model): For UE-sided model at least for BM Case-1, support configuring only one resource set (Set B) for CSI report generation and inference results reporting.
- Proposal 15 (Measurement report for NW-sided model): For NW-sided model BM-Case 2, support reporting Differential L1-RSRP to reduce overhead by communicating relative changes rather than absolute values.
- Proposal 19 (Inference report at NW sided Model): Consider M = 256 as the starting point for the maximum number of beams reported, consistent with study item agreements.
- Proposal 24 (Beam Information): For NW-Sided Model inference when M < N, consider Option 2: Utilize a bit map to indicate reported beams and include one beam index for the largest measured L1-RSRP.
- Proposal 25 (Inference result report for UE-sided model): For UE-sided model BM-Case 1, convey ranking information of predicted Top K beams through the order of reported information, with the first beam having the highest predicted RSRP or probability.
- Proposal 27 (Performance monitoring): Consider Top-K beam prediction accuracy report for UE-assisted performance monitoring in BM-Case1 and BM-Case2.
- Proposal 31 (Performance monitoring): For UE-assisted performance monitoring, configure the resource set(s) for monitoring within the existing CSI report configuration used for inference to minimize signaling overhead.
- Proposal 33 (Beam indication): For BM-Case 2, extend Rel-17 TCI state activation/indication signaling methods, with a maximum number (N) of joint TCI states suggested between 2 and 4.
- Proposal 35 (Beam indication): For TCI state configuration in BM-Case 2, use historic TCI states for predicting N future TCI states along with Set B historic measurements, configured with Set A, Set B, and Associated ID.