Ericsson · 9.1.3
Specification support for CSI prediction ·
RAN1#120 · Source verification
Claude's delta
strengthened
vs RAN1#119
Ericsson hardened its opposition to consistency enhancements by consolidating per-aspect arguments into a blanket conclusion of inapplicability. They refined their proposal by specifying the reuse of the functionality-based LCM framework and requiring the typeII-Doppler-r18' codebook format for both predicted and ground-truth CSI. They narrowed the intermediate KPI scope to SGCS only, explicitly excluding NMSE, and maintained their opposition to Type 2 monitoring.
AI-synthesized from contributions · all text is paraphrased
Every position summary on this site is generated by an AI from the actual Tdoc contributions. This page shows you the exact source documents Claude read to produce the summary above, so you can verify it yourself. Click any Tdoc ID to view its detail page, or click "3gpp.org ↗" to read the original on the official 3GPP server.
Contributions at RAN1#120 · 1 doc
AI/ML for CSI prediction
Position extracted by Claude
Ericsson proposes reusing the functionality-based LCM framework from UE-sided beam management use cases for CSI prediction, specifically leveraging legacy CSI-RS configurations with enhancements for training data association. They require the use of 'typeII-Doppler-r18' codebook format for both predicted CSI and ground-truth labels to ensure testable performance metrics, and they oppose supporting Type 2 performance monitoring due to high overhead and NW complexity. Ericsson argues inapplicability of consistency specification enhancements for training/inference, presenting technical evidence that NW antenna tilt and TXRU mapping variations cause negligible degradation (0-4% for tilt, -1~4% for TXRU). They propose supporting combined periodic and aperiodic CSI-RS configurations to address performance issues with long 20 ms periodicities, and they restrict the intermediate KPI to SGCS only, excluding NMSE.
Summary
Ericsson presents proposals for the normative phase of UE-sided CSI prediction in Rel-19, focusing on functionality-based LCM, data collection, and performance monitoring. The document contains 14 proposals and 18 observations, arguing that no specification enhancements are needed to ensure consistency between training and inference due to negligible performance degradation from NW-side conditions like antenna tilt and TXRU mapping.
Prior contributions at RAN1#119 · 1 doc · Nov 18, 2024
AI/ML for CSI prediction
Position extracted by Claude
Ericsson argues inapplicability of the inconsistency issue identified for UE-sided spatial beam prediction to the UE-sided CSI prediction use case, which relies on temporal domain correlation rather than spatial beam sets. They conclude that no specification enhancement is required to ensure consistency between training and inference regarding UE speed, deployment scenario, carrier frequency, UE distribution, NW antenna tilt, or NW TXRU mapping, citing negligible performance degradation (0-4% for tilt, -1~4% for TXRU mapping) in generalization evaluations. They propose studying specification impacts on CSI-RS configuration to indicate the association between CSI-RS resources in the observation window and ground-truth labels in the prediction window for both training and monitoring data collection. They support specification impacts for inference to enable combined periodic and aperiodic (or semi-persistent) CSI-RS configurations to improve prediction performance with long periodicities like 20 ms. They oppose Type 2 based performance monitoring, citing large reporting overhead and significant NW complexity.
Summary
Ericsson presents evaluation results for UE-sided AI/ML CSI prediction, concluding that no specification enhancements are needed to ensure consistency between training and inference regarding UE speed, deployment scenario, carrier frequency, NW antenna tilt, or TXRU mapping, as generalization performance degradation is negligible. The document proposes studying specification impacts on CSI-RS configuration to support data collection for training and monitoring, specifically requiring indications of association between observation and prediction window resources, and supports combining periodic and aperiodic CSI-RS for inference to improve performance with long periodicities.
How this was derived
Claude extracted the "position extracted" field above directly from each Tdoc during summarization.
For the delta summary at the top, Claude compared Ericsson's consolidated stance at RAN1#120
against their stance at RAN1#119 and classified the change as
strengthened.
Always verify critical claims against the original Tdocs linked above.