Spreadtrum · 9.1.3

Spreadtrum proposes using an associated ID, configured within the CSI framework, to ensure consistency between training and inference for UE-sided CSI prediction models, arguing that performance monitoring-based approaches cause unacceptable performance loss due to trial-and-error processes. They prefer UE-side data collection over network-side collection to avoid significant reporting overhead and model transfer complexities, suggesting that NW configuration or UE requests should trigger this collection. For inference, they propose reusing Rel-18 MIMO CSI-RS configurations to reduce specification impact. Regarding monitoring, they support Type 1 and Type 3 monitoring using intermediate KPIs like SGCS, while explicitly deprioritizing Type 2 monitoring due to the high overhead of reporting ground-truth CSI to the gNB. They further suggest that gNB should indicate the association between prediction and ground-truth CSI-RS resources to facilitate accurate metric calculation.

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.