R1-2409626
discussion
Discussion on AIML for CSI prediction
From Spreadtrum
Spreadtrum's prior position on
9.1.3
at
RAN1#118bis
· AI-synthesized, paraphrased
verify sources →
Advocates for reusing existing AI beam management conclusions and associated ID mechanisms for CSI prediction to minimize workload. Opposes performance monitoring-based approaches, arguing they would cause significant performance loss due to trial-and-error processes.
Summary
Spreadtrum discusses the consistency of training and inference for UE-sided CSI prediction models, proposing the reuse of the 'associated ID' mechanism from Beam Management to ensure network-side conditions remain consistent. The document contains two main proposals: using the associated ID to guarantee consistency and configuring it within the existing CSI framework.
Position
Spreadtrum argues that the 'associated ID' mechanism, previously introduced for Beam Management (AI-BM), should be reused for CSI prediction to ensure consistency of network-side additional conditions across training and inference. They present a technical case against 'performance monitoring based' approaches (Option 2), arguing that such methods require a trial-and-error process causing significant performance loss and cannot distinguish consistency issues from other degradation factors. Consequently, they prefer Option 1, where the UE assumes consistency is guaranteed if training and inference data share the same associated ID. Furthermore, they propose that the associated ID for CSI prediction should be configured within the existing CSI framework, leveraging the fact that reference resources for channel measurement are already defined there.
Key proposals
- Proposal 1 (Sec Further study on consistency of training and inference): For CSI prediction, associated ID can be used to ensure consistency between training and inference.
- Proposal 2 (Sec Further study on consistency of training and inference): For CSI prediction, associated ID can be configured within CSI framework.